Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models
24.1K Pulls 6 Tags Updated 2 days ago
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
196 Pulls 4 Tags Updated 16 hours ago
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
5,421 Pulls 15 Tags Updated 2 days ago
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
1,384 Pulls 1 Tag Updated yesterday
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
39.5K Pulls 6 Tags Updated 5 days ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
9,172 Pulls 6 Tags Updated 6 days ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
110.5K Pulls 16 Tags Updated 5 days ago
The most powerful vision-language model in the Qwen model family to date.
794.2K Pulls 59 Tags Updated 1 month ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
5.3M Pulls 5 Tags Updated 2 months ago
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
74.5M Pulls 35 Tags Updated 5 months ago
Alibaba's performant long context models for agentic and coding tasks.
1.3M Pulls 10 Tags Updated 2 months ago
The current, most capable model that runs on a single GPU.
28.4M Pulls 29 Tags Updated 1 week ago
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
107.7M Pulls 93 Tags Updated 1 year ago
Meta's Llama 3.2 goes small with 1B and 3B models.
50M Pulls 63 Tags Updated 1 year ago
A high-performing open embedding model with a large token context window.
47.9M Pulls 3 Tags Updated 1 year ago
The 7B model released by Mistral AI, updated to version 0.3.
23.3M Pulls 84 Tags Updated 5 months ago
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
18.2M Pulls 133 Tags Updated 1 year ago
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
15.2M Pulls 58 Tags Updated 2 months ago
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
15.2M Pulls 72 Tags Updated 1 year ago
Meta Llama 3: The most capable openly available LLM to date
13M Pulls 68 Tags Updated 1 year ago