Average Ratings 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

No User Reviews. Be the first to provide a review:

Write a Review

Description

BaseRT offers a robust inference runtime for LLMs specifically optimized for Apple Silicon, allowing developers to seamlessly access models from Hugging Face, engage in local conversations, or utilize an API compatible with OpenAI through a single command-line interface. Enhanced by meticulously crafted Metal kernels, BaseRT aims to provide exceptional prefill and decoding efficiency on M-series Macs, with benchmark results indicating it performs up to 6.4 times faster in prefill tasks compared to llama.cpp, 3.9 times faster than MLX, and achieves a decoding speed that is 1.33 times quicker. The basert CLI is equipped to manage tasks such as model downloading, conversion, interactive chat, serving capabilities, completion generation, benchmarking, inspection, and bundle signing. Its server functionalities are extensive, encompassing chat interactions, text completions, embeddings, transcription services, tool calls, continuous batching, paged key-value caching, and prefix caching, with support for models that can handle text, vision, and audio data. BaseRT employs a proprietary .base model format that incorporates Q2–Q8 affine quantization, optional AWQ calibration, and signed bundles, and it is capable of converting GGUF, Hugging Face, and MLX checkpoints. Furthermore, this innovative runtime is tailored to maximize the capabilities of Apple Silicon, making it an essential tool for developers in the AI space.

Description

Incbury is a UK-based independent AI firm that creates its own compact language models, referred to as Atom. The Incbury Chat tool functions as an AI assistant designed for various tasks such as conversation, writing, research, and analysis, while also providing capabilities for web searches, project management, and file handling. Additionally, Incbury Code acts as a coding agent that enhances desktop and terminal workflows, featuring sidebars for popular environments like VS Code and Cursor; it is capable of analyzing codebases, suggesting modifications for review, and executing commands and tests. The Incbury API allows developers to utilize Atom with OpenAI-compatible access, enabling the integration of language-model features within applications, which includes functionalities like streaming and function calling. Users can access Chat through a free plan that imposes daily fair-use limits, while the API and Code services operate on a prepaid credit system. Incbury also shares benchmark results alongside examples that outline the limitations of its models. Its diverse range of products is tailored to meet the needs of individuals, developers, startups, and teams who are looking for chat assistance, coding support, or AI-enhanced applications, making it a versatile choice in the AI landscape.

API Access

Has API Yes 

API Access

Has API Yes 

Screenshots View All

Screenshots View All

Integrations

OpenAI Yes 
Cursor No 
Gemma 3 Yes 
Gemma 4 Yes 
Hugging Face Yes 
Llama 3.1 Yes 
Llama 3.2 Yes 
Mistral AI Yes 
Model Context Protocol (MCP) No 
Phi-3 Yes 
Qwen3 Yes 
Qwen3.5 Yes 
Qwen3.6 Yes 
Visual Studio Code No 

Integrations

OpenAI Yes 
Cursor Yes 
Gemma 3 No 
Gemma 4 No 
Hugging Face No 
Llama 3.1 No 
Llama 3.2 No 
Mistral AI No 
Model Context Protocol (MCP) Yes 
Phi-3 No 
Qwen3 No 
Qwen3.5 No 
Qwen3.6 No 
Visual Studio Code Yes 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Pricing Details

£0
Free plan at £0 forever with daily fair-use limits. Pro is £14.99/month and Ultra is £79.99/month, both excluding VAT. Business is £24.99/user/month excl. VAT, with a 2-user minimum. API and Code use prepaid credits; API input is £0.20 per million tokens, cached input £0.05 per million, and output £0.80 per million. Applicable taxes are added at checkout.
Free Trial No 
Free Version Yes 

Deployment

Web-Based No 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac Yes 
Linux No 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App Yes 
iPad App No 
Android App Yes 
Windows Yes 
Mac No 
Linux Yes 
Chromebook No 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Vendor Details

Company Name

Base Compute

Founded

2026

Country

Australia

Website

www.basecompute.co/getbasert

Vendor Details

Company Name

Incbury

Founded

2025

Country

United Kingdom

Website

incbury.co.uk

Product Features

Product Features

Alternatives

Alternatives

AtomCode Reviews

AtomCode

AtomGit
DeepInfer Reviews

DeepInfer

DeepSeek
SinoGate Reviews

SinoGate

SHANXUAN TECHNOLOGY LIMITED
Deep Code Reviews

Deep Code

Chongqing Parsec Technology Co., Ltd.
Cline Reviews

Cline

Cline AI Coding Agent
5.0 out of 5 stars