New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
1.7M Pulls 14 Tags Updated 4 months ago
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
90.3M Pulls 93 Tags Updated 4 months ago
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
20.2K Pulls 17 Tags Updated 9 months ago
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
2,830 Pulls 5 Tags Updated 7 days ago
1,847 Pulls 1 Tag Updated 8 days ago
testing the new version of llama
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.
41.2K Pulls 8 Tags Updated 10 months ago
The ollama model for the 4bit-quantized GGUF version of llama3-8b-chinese-chat (https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-4bit).
6,767 Pulls 2 Tags Updated 11 months ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.
3,891 Pulls 10 Tags Updated 4 months ago
It uses this one Q4_K_M-imat (4.89 BPW) quant for up to 12288 context sizes. for less than 8gb vram
2,671 Pulls 1 Tag Updated 11 months ago
NousResearch/Hermes-3-Llama-3.1-405B
2,005 Pulls 2 Tags Updated 8 months ago
The ollama model for the 4bit-quantized GGUF version of llama3-70b-chinese-chat (https://huggingface.co/shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit).
2,001 Pulls 1 Tag Updated 11 months ago
reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.
716 Pulls 6 Tags Updated 4 weeks ago