llama4

Meta's latest collection of multimodal models.

vision tools 16x17b 128x17b

1.2M Pulls 11 Tags Updated 8 months ago

llama3.1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

tools 8b 70b 405b

110.4M Pulls 93 Tags Updated 1 year ago

llama3.3

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

tools 70b

3.3M Pulls 14 Tags Updated 1 year ago

firefunction-v2

An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

tools 70b

198.2K Pulls 17 Tags Updated 1 year ago

aravhawk/llama4

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.

109b 400b

6,260 Pulls 5 Tags Updated 10 months ago

ingu627/llama4-scout-q4

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.

109b 400b

4,062 Pulls 3 Tags Updated 10 months ago

johanteekens/Llama-4-Scout-17B-16E-Instruct

Works, thanks ollama team for supporting Llama4!

1,836 Pulls 1 Tag Updated 10 months ago

compcj/llama4-scout-ud-q2-k-xl

unsloth's v2.0 dynamic quants of Llama-4-Scout-17B-16E-Instruct-GGUF, Q2_K_XL(2.71-bit)

tools

476 Pulls 1 Tag Updated 9 months ago

dokterbob/unsloth-llama4-scout

tools

76 Pulls 1 Tag Updated 8 months ago

rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model which is a derivative of Meta Llama-3.3-70B-Instruct. It is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as RAG and tool calling.

328 Pulls 4 Tags Updated 3 months ago

fackingamatherae/Llama_3.5_Abliterated_4

108 Pulls 1 Tag Updated 1 month ago

aadi19/olympus-coder

AI-powered coding assistant built on CodeLlama 13B. Boost productivity 4-6x with intelligent code generation, debugging, and multi-language support

120 Pulls 1 Tag Updated 4 months ago

mirage335/Llama-3_3-Valkyrie-49B-v1-INSTRUCT-virtuoso

Generates excellent search queries, title summaries, etc. Substantial track record. IQ2_XXS - Adequate for the strengths of this AI LLM model. Compatible with ~16GB VRAM. INSTRUCT version - should NOT generate thinking tokens.

tools

70 Pulls 1 Tag Updated 3 months ago

mirage335/Llama-3_3-Nemotron-Super-49B-v1_5-virtuoso

Recommended for agentic AI systems. Apparently relatively decent long-horizon and complex problem solving ability. Significant track record. IQ2_XXS - Apparently adequate. Compatible with ~16GB VRAM.

52 Pulls 1 Tag Updated 3 months ago

mirage335/gpt-oss-20b-virtuoso

Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.

tools thinking

50 Pulls 1 Tag Updated 2 months ago

JollyLlama/GLM-4-32B-0414-Q4_K_M

This model requires Ollama v0.6.6 or later

5,412 Pulls 1 Tag Updated 10 months ago

mirage335/gpt-oss-120b-virtuoso

Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.

tools thinking

41 Pulls 1 Tag Updated 2 months ago

MHKetbi/nvidia_Llama-3.3-Nemotron-Super-49B-v1

reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.

2,594 Pulls 6 Tags Updated 11 months ago

catsarethebest/llama3.2-4oClaude

Llama3.2 1b trained on data distilled from gpt4o, claude3.5 and claude opus

tools

2,397 Pulls 2 Tags Updated 7 months ago

itzune/latxa

Latxa is based on Llama-3.1, which is trained on a Basque corpus comprising 4.3M documents and 4.2B tokens using language adaptation techniques.

tools 8b

34 Pulls 3 Tags Updated 4 months ago