Alternatives to LFM2.5

NVIDIA Nemotron 3.5 Super VL is a multimodal foundation model developed for AI agents that require reasoning, visual understanding, coding, and multistep task execution. Its 120-billion-parameter mixture-of-experts architecture activates approximately 12 billion parameters per token, enabling efficient inference while maintaining substantial model capacity. The model processes text, images, documents, and video within a unified system that combines multimodal interpretation with instruction following and tool use. Its document intelligence capabilities include extracting information from tables, analyzing charts, interpreting page layouts, and processing multipage documents. Video understanding features support visual information retrieval, content review, incident analysis, and reasoning across recorded sequences. The model also supports software engineering tasks such as code analysis, error identification, debugging, testing, and recommending fixes. Developers can customize Nemotron 3.5 Super VL using NVIDIA NeMo for supervised fine-tuning, low-rank adaptation, and reinforcement learning with domain-specific data. Its inference optimizations include speculative decoding, context reuse, multi-token prediction, and NVFP4 quantization to improve throughput and reduce computational requirements. The model is available with open weights and supports deployment across compatible local hardware, enterprise data centers, and cloud infrastructure.

Muse Spark Open is an open-weight foundation model developed by Meta to support multimodal reasoning, autonomous agents, and complex software development tasks. The model features 816 billion total parameters with approximately 42 billion active parameters and a context window supporting up to one million tokens. Its architecture is designed to process multimodal information while maintaining context across lengthy workflows, extensive codebases, and multistep assignments. Muse Spark Open provides capabilities for software engineering, code generation, debugging, application development, and automated testing. Its agentic functionality supports external tool interactions, task planning, computer-based workflows, and execution of complex objectives over extended sessions. The model can run locally using two Apple M5 Ultra Mac Studio systems with the MLX framework, enabling organizations to process information without relying on hosted inference services. Developers can deploy the model through SGLang, vLLM, TensorRT-LLM, Hugging Face Transformers, llama.cpp, and other supported inference engines. Customization is supported through PyTorch and TorchTitan, allowing organizations to adapt the model to specialized applications and workflows. Muse Spark Open is distributed under the Muse Model License and is available through Hugging Face, major cloud model repositories, and hosted API providers including Together AI, Fireworks AI, and OpenRouter.

Inkling is Thinking Machines’ open-weights foundation model built for customization, multimodal reasoning, and agentic AI workflows. The model uses a Mixture-of-Experts architecture with 975 billion total parameters and 41 billion active parameters, making it large in capacity while activating only a subset of experts per token. Inkling supports up to a 1 million token context window and was pretrained on 45 trillion tokens spanning text, images, audio, and video. It is designed as a broad generalist model with strengths across coding, reasoning, instruction following, factuality, tool use, vision, audio understanding, forecasting, and safety. Developers can tune its thinking effort to trade off latency, cost, and performance, which is useful for production systems that need efficient reasoning at scale. Inkling can be fine-tuned on Tinker, tested in the Inkling Playground, and deployed through partners such as TogetherAI, Fireworks, Modal, Databricks, Baseten, vLLM, SGLang, llama.cpp, and Hugging Face transformers. The model can generate applications, operate tools, create styled artifacts, reason over visual and audio inputs, and support long refinement loops for collaborative work. Thinking Machines also previewed Inkling-Small, a lighter Mixture-of-Experts model with 276 billion total parameters and 12 billion active parameters for lower-cost and lower-latency workloads. By combining open weights, multimodal training, agentic capabilities, efficient reasoning, and fine-tuning support, Inkling gives builders a flexible AI foundation for specialized products and workflows.

NVIDIA Nemotron 3.5 Bolt is a series of efficient AI models developed by NVIDIA for running autonomous agents and conversational applications directly on local hardware. The family consists of Bolt 74B-A9B 24GB and Bolt E4B 4GB, which address different performance and memory requirements. Bolt 74B-A9B uses a mixture-of-experts architecture with 74 billion total parameters and approximately 9 billion active parameters to balance reasoning capabilities with computational efficiency. Native 2-bit quantization enables the model to operate within a 24GB memory footprint on supported NVIDIA systems. Its agentic capabilities include web research, code generation, software debugging, information retrieval, and multistep task execution. The model can be integrated with local AI agent frameworks and development tools to complete assignments without sending application workloads to external inference services. Bolt E4B is optimized for fast conversational responses, multistep interactions, and embedded AI experiences such as virtual assistants and interactive game characters. NVIDIA supports local deployment of the Bolt family across compatible GeForce RTX, RTX PRO, DGX Spark, and Jetson hardware, depending on the model variant. Bolt 74B-A9B is available with open weights through Hugging Face and supports inference tools including llama.cpp, Ollama, LM Studio, Unsloth, and vLLM.

Qwen2 represents a collection of extensive language models crafted by the Qwen team at Alibaba Cloud. This series encompasses a variety of models, including base and instruction-tuned versions, with parameters varying from 0.5 billion to an impressive 72 billion, showcasing both dense configurations and a Mixture-of-Experts approach. The Qwen2 series aims to outperform many earlier open-weight models, including its predecessor Qwen1.5, while also striving to hold its own against proprietary models across numerous benchmarks in areas such as language comprehension, generation, multilingual functionality, programming, mathematics, and logical reasoning. Furthermore, this innovative series is poised to make a significant impact in the field of artificial intelligence, offering enhanced capabilities for a diverse range of applications.

Tülu 3 is a cutting-edge language model created by the Allen Institute for AI (Ai2) that aims to improve proficiency in fields like knowledge, reasoning, mathematics, coding, and safety. It is based on the Llama 3 Base and undergoes a detailed four-stage post-training regimen: careful prompt curation and synthesis, supervised fine-tuning on a wide array of prompts and completions, preference tuning utilizing both off- and on-policy data, and a unique reinforcement learning strategy that enhances targeted skills through measurable rewards. Notably, this open-source model sets itself apart by ensuring complete transparency, offering access to its training data, code, and evaluation tools, thus bridging the performance divide between open and proprietary fine-tuning techniques. Performance assessments reveal that Tülu 3 surpasses other models with comparable sizes, like Llama 3.1-Instruct and Qwen2.5-Instruct, across an array of benchmarks, highlighting its effectiveness. The continuous development of Tülu 3 signifies the commitment to advancing AI capabilities while promoting an open and accessible approach to technology.

The NVIDIA Llama Nemotron family comprises a series of sophisticated language models that are fine-tuned for complex reasoning and a wide array of agentic AI applications. These models shine in areas such as advanced scientific reasoning, complex mathematics, coding, following instructions, and executing tool calls. They are designed for versatility, making them suitable for deployment on various platforms, including data centers and personal computers, and feature the ability to switch reasoning capabilities on or off, which helps to lower inference costs during less demanding tasks. The Llama Nemotron series consists of models specifically designed to meet different deployment requirements. Leveraging the foundation of Llama models and enhanced through NVIDIA's post-training techniques, these models boast a notable accuracy improvement of up to 20% compared to their base counterparts while also achieving inference speeds that can be up to five times faster than other leading open reasoning models. This remarkable efficiency allows for the management of more intricate reasoning challenges, boosts decision-making processes, and significantly lowers operational expenses for businesses. Consequently, the Llama Nemotron models represent a significant advancement in the field of AI, particularly for organizations seeking to integrate cutting-edge reasoning capabilities into their systems.

Recursive Flint is an advanced language model featuring 40 billion parameters, designed as a mixture-of-experts specifically for coding tasks executed locally. It engages around 2.5 billion parameters for each token processed, enabling sophisticated reasoning, multi-turn tool utilization, and accommodating context windows as extensive as 512,000 tokens. Developers can leverage Flint within coding agents to analyze codebases, rectify bugs, develop new features, and create tests while executing inference directly on their own hardware. The model's weights are made available under the Apache 2.0 license, promoting accessibility. Flint is compatible with various platforms such as llama.cpp, Ollama, Unsloth, LM Studio, vLLM, and SGLang; additionally, Recursive offers rec, an inference engine that is specifically optimized for use with Apple Silicon M4 Pro and M5 Pro/Max chips. Comprehensive setup documentation and practical examples are provided to assist developers in executing the model on local machines. Flint serves as a valuable tool for developers and technical teams aiming to effectively run and customize a code-centric model tailored to their specific system requirements. This innovative approach empowers users to enhance their coding capabilities and streamline development processes more efficiently than ever before.

Mistral 7B is a language model with 7.3 billion parameters that demonstrates superior performance compared to larger models such as Llama 2 13B on a variety of benchmarks. It utilizes innovative techniques like Grouped-Query Attention (GQA) for improved inference speed and Sliding Window Attention (SWA) to manage lengthy sequences efficiently. Released under the Apache 2.0 license, Mistral 7B is readily available for deployment on different platforms, including both local setups and prominent cloud services. Furthermore, a specialized variant known as Mistral 7B Instruct has shown remarkable capabilities in following instructions, outperforming competitors like Llama 2 13B Chat in specific tasks. This versatility makes Mistral 7B an attractive option for developers and researchers alike.

Introducing the next iteration of our open-source large language model, this version features model weights along with initial code for the pretrained and fine-tuned Llama language models, which span from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been developed using an impressive 2 trillion tokens and offer double the context length compared to their predecessor, Llama 1. Furthermore, the fine-tuned models have been enhanced through the analysis of over 1 million human annotations. Llama 2 demonstrates superior performance against various other open-source language models across multiple external benchmarks, excelling in areas such as reasoning, coding capabilities, proficiency, and knowledge assessments. For its training, Llama 2 utilized publicly accessible online data sources, while the fine-tuned variant, Llama-2-chat, incorporates publicly available instruction datasets along with the aforementioned extensive human annotations. Our initiative enjoys strong support from a diverse array of global stakeholders who are enthusiastic about our open approach to AI, including companies that have provided valuable early feedback and are eager to collaborate using Llama 2. The excitement surrounding Llama 2 signifies a pivotal shift in how AI can be developed and utilized collectively.

EXAONE Deep represents a collection of advanced language models that are enhanced for reasoning, created by LG AI Research, and come in sizes of 2.4 billion, 7.8 billion, and 32 billion parameters. These models excel in a variety of reasoning challenges, particularly in areas such as mathematics and coding assessments. Significantly, the EXAONE Deep 2.4B model outshines other models of its size, while the 7.8B variant outperforms both open-weight models of similar dimensions and the proprietary reasoning model known as OpenAI o1-mini. Furthermore, the EXAONE Deep 32B model competes effectively with top-tier open-weight models in the field. The accompanying repository offers extensive documentation that includes performance assessments, quick-start guides for leveraging EXAONE Deep models with the Transformers library, detailed explanations of quantized EXAONE Deep weights formatted in AWQ and GGUF, as well as guidance on how to run these models locally through platforms like llama.cpp and Ollama. Additionally, this resource serves to enhance user understanding and accessibility to the capabilities of EXAONE Deep models.

Z-Image is a family of open-source image generation foundation models created by Alibaba's Tongyi-MAI team, utilizing a Scalable Single-Stream Diffusion Transformer architecture to produce both photorealistic and imaginative images from textual descriptions with only 6 billion parameters, which enhances its efficiency compared to many larger models while maintaining competitive quality and responsiveness to instructions. This model family comprises several variants, including Z-Image-Turbo, a distilled version designed for rapid inference that achieves results with as few as eight function evaluations and sub-second generation times on compatible GPUs; Z-Image, the comprehensive foundation model tailored for high-fidelity creative outputs and fine-tuning processes; Z-Image-Omni-Base, a flexible base checkpoint aimed at fostering community-driven advancements; and Z-Image-Edit, specifically optimized for image-to-image editing tasks while demonstrating strong adherence to instructions. Each variant of Z-Image serves distinct purposes, catering to a wide range of user needs within the realm of image generation.

The latest iteration of the open-source AI model, which can be fine-tuned and deployed in various environments, is now offered in multiple versions, including 1B, 3B, 11B, and 90B, alongside the option to continue utilizing Llama 3.1. Llama 3.2 comprises a series of large language models (LLMs) that come pretrained and fine-tuned in 1B and 3B configurations for multilingual text only, while the 11B and 90B models accommodate both text and image inputs, producing text outputs. With this new release, you can create highly effective and efficient applications tailored to your needs. For on-device applications, such as summarizing phone discussions or accessing calendar tools, the 1B or 3B models are ideal choices. Meanwhile, the 11B or 90B models excel in image-related tasks, enabling you to transform existing images or extract additional information from images of your environment. Overall, this diverse range of models allows developers to explore innovative use cases across various domains.

Qwen2.5-1M, an open-source language model from the Qwen team, has been meticulously crafted to manage context lengths reaching as high as one million tokens. This version introduces two distinct model variants, namely Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, representing a significant advancement as it is the first instance of Qwen models being enhanced to accommodate such large context lengths. In addition to this, the team has released an inference framework that is based on vLLM and incorporates sparse attention mechanisms, which greatly enhance the processing speed for 1M-token inputs, achieving improvements between three to seven times. A detailed technical report accompanies this release, providing in-depth insights into the design choices and the results from various ablation studies. This transparency allows users to fully understand the capabilities and underlying technology of the models.

OLMo 2 represents a collection of completely open language models created by the Allen Institute for AI (AI2), aimed at giving researchers and developers clear access to training datasets, open-source code, reproducible training methodologies, and thorough assessments. These models are trained on an impressive volume of up to 5 trillion tokens and compete effectively with top open-weight models like Llama 3.1, particularly in English academic evaluations. A key focus of OLMo 2 is on ensuring training stability, employing strategies to mitigate loss spikes during extended training periods, and applying staged training interventions in the later stages of pretraining to mitigate weaknesses in capabilities. Additionally, the models leverage cutting-edge post-training techniques derived from AI2's Tülu 3, leading to the development of OLMo 2-Instruct models. To facilitate ongoing enhancements throughout the development process, an actionable evaluation framework known as the Open Language Modeling Evaluation System (OLMES) was created, which includes 20 benchmarks that evaluate essential capabilities. This comprehensive approach not only fosters transparency but also encourages continuous improvement in language model performance.

Phi-4-reasoning is an advanced transformer model featuring 14 billion parameters, specifically tailored for tackling intricate reasoning challenges, including mathematics, programming, algorithm development, and strategic planning. Through a meticulous process of supervised fine-tuning on select "teachable" prompts and reasoning examples created using o3-mini, it excels at generating thorough reasoning sequences that optimize computational resources during inference. By integrating outcome-driven reinforcement learning, Phi-4-reasoning is capable of producing extended reasoning paths. Its performance notably surpasses that of significantly larger open-weight models like DeepSeek-R1-Distill-Llama-70B and nears the capabilities of the comprehensive DeepSeek-R1 model across various reasoning applications. Designed for use in settings with limited computing power or high latency, Phi-4-reasoning is fine-tuned with synthetic data provided by DeepSeek-R1, ensuring it delivers precise and methodical problem-solving. This model's ability to handle complex tasks with efficiency makes it a valuable tool in numerous computational contexts.

Kimi K2 represents a cutting-edge series of open-source large language models utilizing a mixture-of-experts (MoE) architecture, with a staggering 1 trillion parameters in total and 32 billion activated parameters tailored for optimized task execution. Utilizing the Muon optimizer, it has been trained on a substantial dataset of over 15.5 trillion tokens, with its performance enhanced by MuonClip’s attention-logit clamping mechanism, resulting in remarkable capabilities in areas such as advanced knowledge comprehension, logical reasoning, mathematics, programming, and various agentic operations. Moonshot AI offers two distinct versions: Kimi-K2-Base, designed for research-level fine-tuning, and Kimi-K2-Instruct, which is pre-trained for immediate applications in chat and tool interactions, facilitating both customized development and seamless integration of agentic features. Comparative benchmarks indicate that Kimi K2 surpasses other leading open-source models and competes effectively with top proprietary systems, particularly excelling in coding and intricate task analysis. Furthermore, it boasts a generous context length of 128 K tokens, compatibility with tool-calling APIs, and support for industry-standard inference engines, making it a versatile option for various applications. The innovative design and features of Kimi K2 position it as a significant advancement in the field of artificial intelligence language processing.

Mistral Large 3 pushes open-source AI into frontier territory with a massive sparse MoE architecture that activates 41B parameters per token while maintaining a highly efficient 675B total parameter design. It sets a new performance standard by combining long-context reasoning, multilingual fluency across 40+ languages, and robust multimodal comprehension within a single unified model. Trained end-to-end on thousands of NVIDIA H200 GPUs, it reaches parity with top closed-source instruction models while remaining fully accessible under the Apache 2.0 license. Developers benefit from optimized deployments through partnerships with NVIDIA, Red Hat, and vLLM, enabling smooth inference on A100, H100, and Blackwell-class systems. The model ships in both base and instruct variants, with a reasoning-enhanced version on the way for even deeper analytical capabilities. Beyond general intelligence, Mistral Large 3 is engineered for enterprise customization, allowing organizations to refine the model on internal datasets or domain-specific tasks. Its efficient token generation and powerful multimodal stack make it ideal for coding, document analysis, knowledge workflows, agentic systems, and multilingual communications. With Mistral Large 3, organizations can finally deploy frontier-class intelligence with full transparency, flexibility, and control.

Falcon-40B is a causal decoder-only model consisting of 40 billion parameters, developed by TII and trained on 1 trillion tokens from RefinedWeb, supplemented with carefully selected datasets. It is distributed under the Apache 2.0 license. Why should you consider using Falcon-40B? This model stands out as the leading open-source option available, surpassing competitors like LLaMA, StableLM, RedPajama, and MPT, as evidenced by its ranking on the OpenLLM Leaderboard. Its design is specifically tailored for efficient inference, incorporating features such as FlashAttention and multiquery capabilities. Moreover, it is offered under a flexible Apache 2.0 license, permitting commercial applications without incurring royalties or facing restrictions. It's important to note that this is a raw, pretrained model and is generally recommended to be fine-tuned for optimal performance in most applications. If you need a version that is more adept at handling general instructions in a conversational format, you might want to explore Falcon-40B-Instruct as a potential alternative.

FLUX 3 Action is a versatile 7B world-action model aimed at enhancing action prediction for robotics and other environments with high latency demands. This model is built upon the multimodal FLUX 3 backbone and has undergone extensive pretraining on vast datasets encompassing images, videos, and audio, with a notable focus on video content. It then goes through a phase of joint video-action training and fine-tuning tailored to specific robotic applications and action frameworks. By utilizing instructions, visual input from cameras, and robot joint angles, FLUX 3 Action is capable of predicting motor commands alongside anticipated visual outcomes, enabling robots to perform actions, reassess their surroundings, and iterate on their plans. This approach contrasts with methods that treat visual prediction and control as separate processes, as FLUX 3 Action integrates future video predictions with action commands, effectively leveraging knowledge gained from extensive video pretraining to refine robot control mechanisms. Impressively, its single-step 7B model achieves a success rate of 38.3% on the RoboLab-120 benchmark, showcasing its effectiveness in real-world applications. Furthermore, this innovative integration of action and perception marks a significant advancement in the field of robotic control.

Beam represents Reflection’s inaugural open-weight model, characterized as a sparse Mixture-of-Experts framework featuring a staggering 501 billion parameters, of which 23 billion are actively utilized, specifically crafted for tasks involving coding, reasoning, and agentic functions. Its prowess is derived from extensive pretraining and reinforcement learning, having been developed using a vast dataset of 23.8 trillion diverse, high-quality tokens sourced from the web, public domains, and proprietary licensed materials. With a targeted emphasis on enhancing coding and agentic capabilities, Beam is engineered to provide competitive open-weight performance while ensuring efficient inference compute. This model adeptly handles a wide array of tasks, including intricate software engineering, terminal operations, STEM activities, web searches, tool utilization, and general knowledge inquiries. Reinforcement learning techniques have been employed to bolster its abilities in multi-step reasoning, tool application, and responsiveness to environmental feedback. Moreover, users have the flexibility to manage the balance between efficiency and performance through an adjustable reasoning effort parameter, thus tailoring the model's output to better suit their specific needs.

Introducing an open-source AI model that can be fine-tuned, distilled, and deployed across various platforms. Our newest instruction-tuned model comes in three sizes: 8B, 70B, and 405B, giving you options to suit different needs. With our open ecosystem, you can expedite your development process using a diverse array of tailored product offerings designed to meet your specific requirements. You have the flexibility to select between real-time inference and batch inference services according to your project's demands. Additionally, you can download model weights to enhance cost efficiency per token while fine-tuning for your application. Improve performance further by utilizing synthetic data and seamlessly deploy your solutions on-premises or in the cloud. Take advantage of Llama system components and expand the model's capabilities through zero-shot tool usage and retrieval-augmented generation (RAG) to foster agentic behaviors. By utilizing 405B high-quality data, you can refine specialized models tailored to distinct use cases, ensuring optimal functionality for your applications. Ultimately, this empowers developers to create innovative solutions that are both efficient and effective.

Mistral Large 4 serves as a versatile multimodal language model, accessible via Mistral’s hosted inference API. It integrates capabilities for instruction adherence, reasoning, and agent-like functions, allowing it to process both images and text simultaneously. This model is designed for developers to facilitate various tasks such as chat completions, structured data outputs, executing functions, answering questions from documents, and enhancing tool-assisted workflows. Its range of applications spans conversational AI, software development assistance, cybersecurity evaluations, financial and legal processes, scientific inquiry, data extraction, and the interpretation of various document types, including charts and images. Aimed at developers, researchers, and organizations within the public sector, Mistral Large 4 is tailored for creating AI-driven applications across numerous fields, including engineering, manufacturing, finance, logistics, and scientific research. Furthermore, its adaptability makes it suitable for both small startups and large enterprises looking to leverage AI technologies effectively.

MedGemma is an innovative suite of Gemma 3 variants specifically designed to excel in the analysis of medical texts and images. This resource empowers developers to expedite the creation of AI applications focused on healthcare. Currently, MedGemma offers two distinct variants: a multimodal version with 4 billion parameters and a text-only version featuring 27 billion parameters. The 4B version employs a SigLIP image encoder, which has been meticulously pre-trained on a wealth of anonymized medical data, such as chest X-rays, dermatological images, ophthalmological images, and histopathological slides. Complementing this, its language model component is trained on a wide array of medical datasets, including radiological images and various pathology visuals. MedGemma 4B can be accessed in both pre-trained versions, denoted by the suffix -pt, and instruction-tuned versions, marked by the suffix -it. For most applications, the instruction-tuned variant serves as the optimal foundation to build upon, making it particularly valuable for developers. Overall, MedGemma represents a significant advancement in the integration of AI within the medical field.

Ai2 OLMoE is a completely open-source mixture-of-experts language model that operates entirely on-device, ensuring that you can experiment with the model in a private and secure manner. This application is designed to assist researchers in advancing on-device intelligence and to allow developers to efficiently prototype innovative AI solutions without the need for cloud connectivity. OLMoE serves as a highly efficient variant within the Ai2 OLMo model family. Discover the capabilities of state-of-the-art local models in performing real-world tasks, investigate methods to enhance smaller AI models, and conduct local tests of your own models utilizing our open-source codebase. Furthermore, you can seamlessly integrate OLMoE into various iOS applications, as the app prioritizes user privacy and security by functioning entirely on-device. Users can also easily share the outcomes of their interactions with friends or colleagues. Importantly, both the OLMoE model and the application code are fully open source, offering a transparent and collaborative approach to AI development. By leveraging this model, developers can contribute to the growing field of on-device AI while maintaining high standards of user privacy.

Tencent Hunyuan represents a comprehensive family of multimodal AI models crafted by Tencent, encompassing a range of modalities including text, images, video, and 3D data, all aimed at facilitating general-purpose AI applications such as content creation, visual reasoning, and automating business processes. This model family features various iterations tailored for tasks like natural language interpretation, multimodal comprehension that combines vision and language (such as understanding images and videos), generating images from text, creating videos, and producing 3D content. The Hunyuan models utilize a mixture-of-experts framework alongside innovative strategies, including hybrid "mamba-transformer" architectures, to excel in tasks requiring reasoning, long-context comprehension, cross-modal interactions, and efficient inference capabilities. A notable example is the Hunyuan-Vision-1.5 vision-language model, which facilitates "thinking-on-image," allowing for intricate multimodal understanding and reasoning across images, video segments, diagrams, or spatial information. This robust architecture positions Hunyuan as a versatile tool in the rapidly evolving field of AI, capable of addressing a diverse array of challenges.

CodeGemma represents an impressive suite of efficient and versatile models capable of tackling numerous coding challenges, including middle code completion, code generation, natural language processing, mathematical reasoning, and following instructions. It features three distinct model types: a 7B pre-trained version designed for code completion and generation based on existing code snippets, a 7B variant fine-tuned for translating natural language queries into code and adhering to instructions, and an advanced 2B pre-trained model that offers code completion speeds up to twice as fast. Whether you're completing lines, developing functions, or crafting entire segments of code, CodeGemma supports your efforts, whether you're working in a local environment or leveraging Google Cloud capabilities. With training on an extensive dataset comprising 500 billion tokens predominantly in English, sourced from web content, mathematics, and programming languages, CodeGemma not only enhances the syntactical accuracy of generated code but also ensures its semantic relevance, thereby minimizing mistakes and streamlining the debugging process. This powerful tool continues to evolve, making coding more accessible and efficient for developers everywhere.

Shieldstral is an innovative multimodal safety classifier with a 3B parameter open-weight structure, adept at assessing text, images, and combined text-plus-image content based on dynamically defined policies during inference. Rather than adhering to a static set of harm categories, it approaches moderation as a binary question-and-answer format: users submit a contextual instruction outlining the evaluation criteria and strictness, pose a yes-or-no safety inquiry, and present the content for assessment. The model processes the “yes” and “no” logits to generate a continuous, calibrated safety score, enabling applications to prioritize or rank outcomes based on confidence levels instead of relying on a single categorical label. This design effectively integrates prompt classification, response moderation, refusal detection, toxicity assessment, and multimodal safety evaluation into a singular interface, empowering teams to modify policies without the need for model retraining. Shieldstral's versatility allows it to analyze prompts, responses, pairs of prompts and responses, images, and images paired with text, making it a comprehensive tool for safety evaluation. As such, it represents a significant advancement in the field of content moderation.

Qwen3.5 represents a major advancement in open-weight multimodal AI models, engineered to function as a native vision-language agent system. Its flagship model, Qwen3.5-397B-A17B, leverages a hybrid architecture that fuses Gated DeltaNet linear attention with a high-sparsity mixture-of-experts framework, allowing only 17 billion parameters to activate during inference for improved speed and cost efficiency. Despite its sparse activation, the full 397-billion-parameter model achieves competitive performance across reasoning, coding, multilingual benchmarks, and complex agent evaluations. The hosted Qwen3.5-Plus version supports a one-million-token context window and includes built-in tool use for search, code interpretation, and adaptive reasoning. The model significantly expands multilingual coverage to 201 languages and dialects while improving encoding efficiency with a larger vocabulary. Native multimodal training enables strong performance in image understanding, video processing, document analysis, and spatial reasoning tasks. Its infrastructure includes FP8 precision pipelines and heterogeneous parallelism to boost throughput and reduce memory consumption. Reinforcement learning at scale enhances multi-step planning and general agent behavior across text and multimodal environments. Overall, Qwen3.5 positions itself as a high-efficiency foundation for autonomous digital agents capable of reasoning, searching, coding, and interacting with complex environments.

Reka Flash 3 is a cutting-edge multimodal AI model with 21 billion parameters, crafted by Reka AI to perform exceptionally well in tasks such as general conversation, coding, following instructions, and executing functions. This model adeptly handles and analyzes a myriad of inputs, including text, images, video, and audio, providing a versatile and compact solution for a wide range of applications. Built from the ground up, Reka Flash 3 was trained on a rich array of datasets, encompassing both publicly available and synthetic information, and it underwent a meticulous instruction tuning process with high-quality selected data to fine-tune its capabilities. The final phase of its training involved employing reinforcement learning techniques, specifically using the REINFORCE Leave One-Out (RLOO) method, which combined both model-based and rule-based rewards to significantly improve its reasoning skills. With an impressive context length of 32,000 tokens, Reka Flash 3 competes effectively with proprietary models like OpenAI's o1-mini, making it an excellent choice for applications requiring low latency or on-device processing. The model operates at full precision with a memory requirement of 39GB (fp16), although it can be efficiently reduced to just 11GB through the use of 4-bit quantization, demonstrating its adaptability for various deployment scenarios. Overall, Reka Flash 3 represents a significant advancement in multimodal AI technology, capable of meeting diverse user needs across multiple platforms.

Devstral is a collaborative effort between Mistral AI and All Hands AI, resulting in an open-source large language model specifically tailored for software engineering. This model demonstrates remarkable proficiency in navigating intricate codebases, managing edits across numerous files, and addressing practical problems, achieving a notable score of 46.8% on the SWE-Bench Verified benchmark, which is superior to all other open-source models. Based on Mistral-Small-3.1, Devstral boasts an extensive context window supporting up to 128,000 tokens. It is designed for optimal performance on high-performance hardware setups, such as Macs equipped with 32GB of RAM or Nvidia RTX 4090 GPUs, and supports various inference frameworks including vLLM, Transformers, and Ollama. Released under the Apache 2.0 license, Devstral is freely accessible on platforms like Hugging Face, Ollama, Kaggle, Unsloth, and LM Studio, allowing developers to integrate its capabilities into their projects seamlessly. This model not only enhances productivity for software engineers but also serves as a valuable resource for anyone working with code.

Seed2.0 Mini represents the most compact version of ByteDance's Seed2.0 line of versatile multimodal agent models, crafted for efficient high-throughput inference and dense deployment, while still embodying the essential strengths found in its larger counterparts regarding multimodal understanding and instruction adherence. This Mini variant, alongside Pro and Lite siblings, is particularly fine-tuned for handling high-concurrency and batch generation tasks, proving itself ideal for scenarios where the ability to process numerous requests simultaneously is as crucial as its overall capability. In line with other models in the Seed2.0 family, it showcases notable improvements in visual reasoning and motion perception, excels at extracting structured information from intricate inputs such as text and images, and effectively carries out multi-step instructions. However, in exchange for enhanced inference speed and cost efficiency, it sacrifices some degree of raw reasoning power and output quality, ensuring that it remains a practical option for various applications. As a result, Seed2.0 Mini strikes a balance between performance and efficiency, appealing to developers seeking to optimize their systems for scalable solutions.

ERNIE-Image is a text-to-image generation model created by Baidu that aims to produce high-quality images with precise adherence to instructions and enhanced control. Utilizing a single-stream Diffusion Transformer (DiT) framework with approximately 8 billion parameters, it achieves leading performance among open-weight image models while maintaining operational efficiency. The model features an integrated prompt enhancement mechanism that transforms basic user inputs into more elaborate and structured descriptions, thereby elevating the quality and coherence of the images it generates. It is particularly adept at complex instruction adherence, enabling it to accurately depict text within images, manage structured layouts, and create multi-element compositions, making it ideal for applications such as posters, comics, and multi-panel designs. Furthermore, ERNIE-Image accommodates multilingual prompts in languages such as English, Chinese, and Japanese, which enhances its accessibility and usability across different regions. This versatility may lead to a wider range of creative applications, allowing users to express their ideas visually in diverse contexts.

The Mixtral 8x7B model is an advanced sparse mixture of experts (SMoE) system that boasts open weights and is released under the Apache 2.0 license. This model demonstrates superior performance compared to Llama 2 70B across various benchmarks while achieving inference speeds that are six times faster. Recognized as the leading open-weight model with a flexible licensing framework, Mixtral also excels in terms of cost-efficiency and performance. Notably, it competes with and often surpasses GPT-3.5 in numerous established benchmarks, highlighting its significance in the field. Its combination of accessibility, speed, and effectiveness makes it a compelling choice for developers seeking high-performing AI solutions.

Laguna XS.2 represents Poolside’s innovative open-weight coding model, distinguished as the lightest and quickest member of the Laguna series. This model features a total of 33 billion parameters in a Mixture of Experts setup, with 3 billion parameters activated, and has been meticulously trained in-house using 30 trillion tokens. As the latest generation model accessible to the public, it embodies a second-generation architecture and marks Poolside’s inaugural open-weight offering, drawing from insights gained during the training of Laguna M.1 with synthetic data and reinforcement learning techniques. Specifically designed to enhance agentic coding workflows, Laguna XS.2 excels in coding, acting, and rapidly iterating, particularly within Poolside’s coding agent environment. This model is particularly advantageous for developers and teams seeking a lightweight, efficient coding solution rather than a more cumbersome frontier system. Released under the permissive Apache 2.0 license, it empowers the community to assess, fine-tune, quantize, and build upon its weights, fostering a collaborative development atmosphere. In essence, Laguna XS.2 not only provides a robust platform for agentic coding but also encourages innovation and experimentation among its users.

Mistral AI has launched two cutting-edge models designed for on-device computing and edge applications, referred to as "les Ministraux": Ministral 3B and Ministral 8B. These innovative models redefine the standards of knowledge, commonsense reasoning, function-calling, and efficiency within the sub-10B category. They are versatile enough to be utilized or customized for a wide range of applications, including managing complex workflows and developing specialized task-focused workers. Capable of handling up to 128k context length (with the current version supporting 32k on vLLM), Ministral 8B also incorporates a unique interleaved sliding-window attention mechanism to enhance both speed and memory efficiency during inference. Designed for low-latency and compute-efficient solutions, these models excel in scenarios such as offline translation, smart assistants that don't rely on internet connectivity, local data analysis, and autonomous robotics. Moreover, when paired with larger language models like Mistral Large, les Ministraux can effectively function as streamlined intermediaries, facilitating function-calling within intricate multi-step workflows, thereby expanding their applicability across various domains. This combination not only enhances performance but also broadens the scope of what can be achieved with AI in edge computing.

Qwen3.6 is an advanced AI model from Alibaba that builds on previous Qwen releases with a focus on real-world utility and performance. It is designed as a multimodal large language model capable of understanding and generating text while also processing visual and structured data. The model is optimized for coding tasks, enabling developers to handle complex, repository-level programming workflows. Qwen3.6 uses a mixture-of-experts (MoE) architecture, which activates only a portion of its parameters during inference to improve efficiency. This design allows it to deliver strong performance while reducing computational costs. It is available in both proprietary and open-weight versions, giving developers flexibility in deployment. The model supports integration into enterprise systems and cloud platforms, particularly within Alibaba’s ecosystem. Qwen3.6 also introduces stronger agentic capabilities, allowing it to perform multi-step reasoning and more autonomous task execution. It is designed to handle complex workflows, including engineering, analysis, and decision-making tasks. The model emphasizes stability and responsiveness based on developer feedback. Overall, Qwen3.6 provides a scalable and efficient AI solution for coding, automation, and multimodal applications.

Seed2.0 Lite belongs to the Seed2.0 lineup from ByteDance, which encompasses versatile multimodal AI agent models engineered to tackle intricate, real-world challenges while maintaining a harmonious balance between efficiency and performance. This model boasts superior multimodal comprehension and instruction-following skills compared to its predecessors in the Seed series, allowing it to effectively interpret and analyze text, visual components, and structured data for use in production environments. Positioned as a mid-sized option within the family, Lite is fine-tuned to provide high-quality results with quick responsiveness at a reduced cost and faster inference times than the Pro version, while also enhancing the capabilities of earlier models. Consequently, it is well-suited for applications that demand consistent reasoning, extended context comprehension, and the execution of multimodal tasks without necessitating the utmost raw performance levels. Moreover, this accessibility makes Seed2.0 Lite an attractive choice for developers seeking efficiency alongside capabilities in their AI solutions.

The Laguna XS 2.1 is an enhanced coding model that operates as an open weight agentic system, ideal for long-duration tasks on local machines. Featuring a 33-billion-parameter Mixture-of-Experts framework with 3 billion parameters activated per token, this model maintains the efficient architecture of Laguna XS.2 while significantly advancing performance in multilingual software engineering and terminal-style tasks. It is specifically engineered to assist coding agents in reviewing repositories, reasoning through intricate changes, utilizing various tools, executing commands, and maintaining continuity throughout extended projects. With a generous 256K context window, the model enables agents to effectively manage extensive codebases, lengthy histories, and complex multi-step workflows. Laguna XS 2.1 benefits from support from platforms like vLLM, SGLang, NVIDIA TensorRT-LLM, Hugging Face Transformers, and Ollama, with plans for native integration with llama.cpp in the future. The model is offered in various checkpoint formats, including BF16, FP8, INT4, and NVFP4, granting developers the flexibility to select between high fidelity and configurations optimized for limited VRAM or computational resources. This adaptability makes it an excellent choice for a wide range of development environments and requirements.

Fullmoon is an innovative, open-source application designed to allow users to engage directly with large language models on their personal devices, prioritizing privacy and enabling offline use. Tailored specifically for Apple silicon, it functions smoothly across various platforms, including iOS, iPadOS, macOS, and visionOS. Users have the ability to customize their experience by modifying themes, fonts, and system prompts, while the app also works seamlessly with Apple's Shortcuts to enhance user productivity. Notably, Fullmoon is compatible with models such as Llama-3.2-1B-Instruct-4bit and Llama-3.2-3B-Instruct-4bit, allowing for effective AI interactions without requiring internet connectivity. This makes it a versatile tool for anyone looking to harness the power of AI conveniently and privately.

Qwen3.8-27B is a 27B-class open-weights model associated with Alibaba’s Qwen3.8 model family. Alibaba’s Qwen3.8 release positioned the broader family as a top-tier large language model system optimized for coding and professional cowork scenarios. Reports indicate that Qwen3.8-27B was planned to be released as open weights alongside Qwen3.8-Max, giving developers and researchers a more accessible option than the full Max-scale model. The model is designed for users who want strong AI capability in a smaller, more deployable package. Qwen3.8-27B can support workflows such as coding assistance, AI agents, research tasks, document analysis, data work, and self-hosted experimentation. The larger Qwen3.8-Max release is described as targeting coding, research, professional work, and multimodal tasks, and Qwen3.8-27B appears to serve builders who need a more practical model size for local or private infrastructure. QwenCloud documentation confirms that the Qwen3.8 generation includes modern capabilities such as thinking, function calling, built-in tools, and structured output for the Max model. Community discussion and third-party coverage also highlight interest in running Qwen3.8-27B through GGUF and local inference workflows. By combining open-weight accessibility, a 27B-class footprint, Qwen3.8-era capability, and developer-focused use cases, Qwen3.8-27B gives teams a practical model for coding and agentic experimentation.

Solar Mini is an advanced pre-trained large language model that matches the performance of GPT-3.5 while providing responses 2.5 times faster, all while maintaining a parameter count of under 30 billion. In December 2023, it secured the top position on the Hugging Face Open LLM Leaderboard by integrating a 32-layer Llama 2 framework, which was initialized with superior Mistral 7B weights, coupled with a novel method known as "depth up-scaling" (DUS) that enhances the model's depth efficiently without the need for intricate modules. Following the DUS implementation, the model undergoes further pretraining to restore and boost its performance, and it also includes instruction tuning in a question-and-answer format, particularly tailored for Korean, which sharpens its responsiveness to user prompts, while alignment tuning ensures its outputs align with human or sophisticated AI preferences. Solar Mini consistently surpasses rivals like Llama 2, Mistral 7B, Ko-Alpaca, and KULLM across a range of benchmarks, demonstrating that a smaller model can still deliver exceptional performance. This showcases the potential of innovative architectural strategies in the development of highly efficient AI models.

Tiny Aya represents a collection of open-weight multilingual language models developed by Cohere Labs, aimed at providing robust and flexible AI capabilities that function seamlessly on local devices such as smartphones and laptops, all without the need for continuous cloud access. This innovative model is dedicated to facilitating superior text comprehension and generation in over 70 languages, notably including numerous lower-resource languages that typically receive less attention from conventional models. Engineered with lightweight structures comprising around 3.35 billion parameters, Tiny Aya has been fine-tuned for optimal multilingual representation and practical computational efficiency, making it ideal for deployment in edge environments and offline scenarios. Furthermore, the models are designed to support downstream adaptation and instruction tuning, enabling developers to tailor the models’ behaviors for specific use cases while ensuring strong performance across languages. As a result, Tiny Aya not only enhances access to advanced AI solutions but also empowers developers to create customized applications that meet diverse linguistic needs.

The LEAP Edge AI Platform presents a comprehensive on-device AI toolchain that allows developers to create edge AI applications, encompassing everything from model selection to inference directly on the device. This platform features a best-model search engine designed to identify the most suitable model based on specific tasks and device limitations, and it offers a collection of pre-trained model bundles that can be easily downloaded. Additionally, it provides fine-tuning resources, including GPU-optimized scripts, enabling customization of models like LFM2 for targeted applications. With support for vision-enabled functionalities across various platforms such as iOS, Android, and laptops, it also includes function-calling capabilities, allowing AI models to engage with external systems through structured outputs. For seamless deployment, LEAP offers an Edge SDK that empowers developers to load and query models locally, mimicking cloud API functionality while remaining completely offline, along with a model bundling service that facilitates the packaging of any compatible model or checkpoint into an optimized bundle for edge deployment. This comprehensive suite of tools ensures that developers have everything they need to build and deploy sophisticated AI applications efficiently and effectively.

Muse Glimmer is an open-weights model featuring 30 billion parameters, developed by Meta Superintelligence Labs, and is fine-tuned for continuous local agent operations. Its compact design allows it to function on a standard Mac or PC equipped with a single consumer GPU, making it ideal for various tasks such as local agent management, function calling, programming, and LLM-as-a-judge evaluations without reliance on cloud services or internet connectivity. This innovative model integrates advanced capabilities such as long-horizon execution, accurate tool invocation, multimodal comprehension, extended memory for context, and effective instruction following. It is proficient in accomplishing end-to-end tasks as an agent, maintains the ability to engage in multi-step reasoning over lengthy processes, can recover gracefully from failed or unanticipated tool engagements, and interprets interleaved text and images using a specialized perception encoder designed for analyzing screenshots, graphs, and document files. Furthermore, Muse Glimmer is compatible with OpenClaw and other orchestration frameworks, allowing for adjustable reasoning efforts, and has been developed with a diverse dataset encompassing over 100 languages. The model's versatility ensures that it can adapt to various applications, thus enhancing its utility in different domains.