A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
107.8K Pulls 5 Tags Updated 11 months ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
39.8K Pulls 6 Tags Updated 5 days ago
Meta's Llama 3.2 goes small with 1B and 3B models.
50M Pulls 63 Tags Updated 1 year ago
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
2.2M Pulls 21 Tags Updated 10 months ago
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
891.9K Pulls 5 Tags Updated 6 months ago
Magistral is a small, efficient reasoning model with 24B parameters.
829.9K Pulls 5 Tags Updated 6 months ago
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
574.4K Pulls 94 Tags Updated 1 year ago
moondream2 is a small vision language model designed to run efficiently on edge devices.
454.6K Pulls 18 Tags Updated 1 year ago
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
445.9K Pulls 5 Tags Updated 8 months ago
A new small LLaVA model fine-tuned from Phi 3 Mini.
155.4K Pulls 4 Tags Updated 1 year ago
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
133.3K Pulls 17 Tags Updated 1 year ago
The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.
99.6K Pulls 5 Tags Updated 11 months ago
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
74.8K Pulls 17 Tags Updated 1 year ago
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
95.6K Pulls 49 Tags Updated 2 years ago
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
198.7K Pulls 52 Tags Updated 1 year ago
Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.
181.1K Pulls 36 Tags Updated 1 year ago
Open-source medical large language model adapted from Llama 2 to the medical domain.
117.9K Pulls 22 Tags Updated 2 years ago
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
57.3K Pulls 13 Tags Updated 1 year ago
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
420 Pulls 4 Tags Updated 22 hours ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
2.8M Pulls 14 Tags Updated 1 year ago