A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
14.2K Pulls 13 Tags Updated 1 month ago
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
507K Pulls 17 Tags Updated 1 year ago
Light version - GigaChat-3.1-Lightning: it shows the level of GPT-4o in arenas, but at the same time remains compact and fast (quantized Q4_K_M)
533 Pulls 1 Tag Updated 3 months ago
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding
241 Pulls 1 Tag Updated 4 months ago
153 Pulls 1 Tag Updated 4 months ago
21.4K Pulls 11 Tags Updated 1 month ago
This is a AI assistant named RayyianAI and it uses GPT-4 and can think or web search
47 Pulls 1 Tag Updated 5 months ago
A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
27.2K Pulls 13 Tags Updated 1 year 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.
45.8K Pulls 8 Tags Updated 2 years ago
A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
2,786 Pulls 12 Tags Updated 1 year ago
2,160 Pulls 12 Tags Updated 11 months ago
Qwen2.5 0.5B fine-tuned on data distilled from GPT 4.1-Nano, 4o, o3, and o4-mini
599 Pulls 1 Tag Updated 1 year ago
A GPT-4V Level Multimodal LLM on Your Phone
482 Pulls 13 Tags Updated 1 year ago
9 Pulls 2 Tags Updated 7 months 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
557 Pulls 1 Tag Updated 2 years ago
gpt-oss_claude-sonnet4.6 is the GPT-OSS model running on the Claude Sonnet 4.6 system prompt, combining GPT-OSS's open-source foundation with Claude Sonnet 4.6's advanced instructions and behavior.
8,421 Pulls 1 Tag Updated 4 months ago
GPT-oss 20b distilled with Claude Sonnet 4.6 system prompts and customized params, pretty fast response (medium/high thinking).
589 Pulls 1 Tag Updated 2 months ago
15.9K Pulls 1 Tag Updated 1 year ago
Tried my best to make gpt-4o-mini from chevalblanc to be more optimized for CPU usage... and I did
1,426 Pulls 1 Tag Updated 1 year ago
https://habr.com/ru/articles/830332/
1,010 Pulls 1 Tag Updated 1 year ago