Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
112.8K Pulls 2 Tags Updated 3 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.
81.6M Pulls 35 Tags Updated 9 months ago
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
6.5M Pulls 102 Tags Updated 1 year ago
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
668.4K Pulls 49 Tags Updated 1 year ago
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.
2.7M Pulls 85 Tags Updated 1 year ago
Qwen3.5-Gemini-Design enhances the models with an optimized system prompt for better reasoning, coding, and instruction-following performance. Smaller Models may suffer from slower speeds.
484 Pulls 14 Tags Updated 2 days ago
9B coding agent based on Qwen3.5-9B, fine-tuned on 425K real agentic traces from Claude Opus 4.6, GPT-5.4, and Gemini 3.1. Reads before it writes, traces bugs to the root cause, doesn't clobber your existing code.
6,353 Pulls 3 Tags Updated 2 weeks ago
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone
4,822 Pulls 12 Tags Updated 1 month ago
glogwa68: https://huggingface.co/glogwa68/granite-4.0-h-350m-DISTILL-gemini-think
30 Pulls 1 Tag Updated 2 weeks ago
Void Gemini — Flagship AI developed by Void, released As of today, January 4, 2026, Void Gemini Pro stands as our most advanced model, delivering exceptional reasoning, multimodal understanding (text, images, code, and ect.)
523 Pulls 1 Tag Updated 1 week ago
Good for creative thinking and code with math problem solving skills and it is small and efficient
273 Pulls 1 Tag Updated 3 months ago
49 Pulls 1 Tag Updated 3 months ago
34 Pulls 1 Tag Updated 4 months ago
Lexa-Rho is part of Lexa Family with performance approaching that of leading models, such as GPT-5 Thinking, Gemini 2.5 Pro and DeepSeek-R1.
374 Pulls 2 Tags Updated 7 months ago
371 Pulls 1 Tag Updated 8 months ago
Gemini-transfer
11 Pulls 1 Tag Updated 1 month ago
MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.
45.4K Pulls 8 Tags Updated 1 year ago
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models
745 Pulls 24 Tags Updated 1 year ago
minicpm-llama3-2.5-8b-16-v With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max and greatly outperforms other Llama 3-based MLLMs
524 Pulls 1 Tag Updated 1 year ago
269 Pulls 11 Tags Updated 1 year ago