Compare Abliterated Large V2 vs. Inkling

Abliterated Large V2 is a large language model developed by Abliteration AI for cybersecurity research, software engineering, and complex autonomous AI agent tasks. The model is derived from GLM 5.3 and uses a process known as abliteration to modify neural network weights associated with refusal behavior. This approach is intended to reduce content restrictions that can interfere with authorized security assessments, adversarial testing, and technical research. Its one-million-token context window supports processing large codebases, extensive technical documents, and multistep agent execution histories. The model provides advanced reasoning capabilities for programming, debugging, vulnerability reproduction, and technical problem-solving. Its cybersecurity applications include penetration testing research, security control evaluation, AI red teaming, and vulnerability validation in authorized environments. Native function calling and structured output capabilities allow developers to integrate the model with automated tools and external systems. Abliterated Large V2 is hosted using FP8 numerical precision and supports OpenAI-compatible and Anthropic-style API interfaces. The platform also provides automatic prompt caching and a zero-data-retention policy for API prompts and responses by default.

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.