llama4

Meta's latest collection of multimodal models.

vision tools 16x17b 128x17b

1.6M Pulls 11 Tags Updated 10 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

114M 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

3.8M 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

489.5K Pulls 17 Tags Updated 1 year ago

lfm2

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

tools 24b

1.1M Pulls 6 Tags Updated 2 months ago

vinzenzhersche/openclaw-llama4

vision tools

66 Pulls 1 Tag Updated 2 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

693 Pulls 1 Tag Updated 11 months ago

dokterbob/unsloth-llama4-scout

tools

98 Pulls 1 Tag Updated 10 months 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

6,787 Pulls 5 Tags Updated 1 year 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

4,471 Pulls 3 Tags Updated 1 year ago

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

Works, thanks ollama team for supporting Llama4!

2,377 Pulls 1 Tag Updated 1 year ago

coney_/llama3.1-claude-sonnet-4.6

llama.31 using cladue sonnets prompting system

tools

848 Pulls 1 Tag Updated 2 months ago

frob/mradermacher-Llama3.3-8B-Thinking-Heretic-Claude-4.5-Opus

tools thinking

415 Pulls 1 Tag Updated 1 month ago

fackingamatherae/Llama_3.5_Abliterated_4

172 Pulls 1 Tag Updated 4 months ago

anismselmi/sandwich1.0

🥪 sandwich1.0 - LLaMA‑3.2 3.21B (2.0 GB, Q4_K_M) 🤖 Friendly assistant model by Anis Mselmi 🧑‍💻 4GB RAM minimum 🚀

tools

71 Pulls 1 Tag Updated 1 month 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

95 Pulls 1 Tag Updated 5 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.

87 Pulls 1 Tag Updated 5 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

80 Pulls 1 Tag Updated 5 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

79 Pulls 1 Tag Updated 5 months ago

fackingamatherae/Deepseek_Llama_4

39 Pulls 1 Tag Updated 4 months ago