Meta's latest collection of multimodal models.
642.5K Pulls 11 Tags Updated 2 months ago
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
101.3M Pulls 93 Tags Updated 9 months ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
2.4M Pulls 14 Tags Updated 9 months ago
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
31.8K Pulls 17 Tags Updated 1 year ago
Works, thanks ollama team for supporting Llama4!
795 Pulls 1 Tag Updated 4 months ago
The Llama 4 models are Meta's flagship LLMs. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text understanding and generation.
5,963 Pulls 5 Tags Updated 4 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.
3,184 Pulls 3 Tags Updated 4 months ago
unsloth's v2.0 dynamic quants of Llama-4-Scout-17B-16E-Instruct-GGUF, Q2_K_XL(2.71-bit)
256 Pulls 1 Tag Updated 3 months ago
52 Pulls 1 Tag Updated 2 months ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.
21.7K Pulls 10 Tags Updated 8 months ago
This model requires Ollama v0.6.6 or later
3,507 Pulls 1 Tag Updated 4 months ago
NousResearch/Hermes-3-Llama-3.1-405B
2,651 Pulls 2 Tags Updated 1 year ago
reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.
2,138 Pulls 6 Tags Updated 5 months ago
403 Pulls 1 Tag Updated 4 months ago
https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1-4bit
387 Pulls 1 Tag Updated 1 year ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model. I-Quants models.
269 Pulls 9 Tags Updated 8 months ago
Brainstorm 40x by DavidAU available in [F16, q8_0, q6_K, q4_K_S]
105 Pulls 4 Tags Updated 6 months ago
Llama-3.2-1B-Instruct-bnb-4bit finetuned for Indonesian Language
71 Pulls 1 Tag Updated 9 months ago
Vicky is a 4.1GB model from the Llama model family, with 7 billion parameters. It is quantized to 4-bit precision. The model is designed for Open stack Tool selection for user or developer. License: Apache License Version 2.0
32 Pulls 1 Tag Updated 1 year ago
16 Pulls 1 Tag Updated 6 months ago