全球开源模型频道

Meta's Llama 3.2 goes small with 1B and 3B models.

ollama run llama3.2

本地助手与 coding 入门标准；8–12GB Q4 舒适。

ollama run llama3.1:8b

Meta Llama 3: The most capable openly available LLM to date

ollama run llama3

开源旗舰对话质量；单卡 48GB+ Q4 或双 24GB TP。

ollama run llama3.3:70b

A large language model that can use text prompts to generate and discuss code.

ollama run codellama

Llama 4 多模态 MoE 线；激活参数可控，机房/大显存。

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

ollama run llama2

The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

ollama run tinyllama

更大 MoE；多卡/机房推理为主。

Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.

ollama run dolphin-llama3

Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.

ollama run llama-guard3

Llama 2 based model fine tuned to improve Chinese dialogue ability.

ollama run llama2-chinese

Uncensored Llama 2 model by George Sung and Jarrad Hope.

ollama run llama2-uncensored

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

ollama run llama3-chatqa

Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

ollama run llama3.2-vision

Meta's latest collection of multimodal models.

ollama run llama4

A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

ollama run llava-llama3

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

ollama run llama-pro

This model extends LLama-3 8B's context length from 8k to over 1m tokens.

ollama run llama3-gradient

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

ollama run llama3-groq-tool-use

Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

ollama run medllama2

Code generation model based on Code Llama.

ollama run phind-codellama

An extension of Llama 2 that supports a context of up to 128k tokens.

ollama run yarn-llama2

Hugging Face GGUF · downloads ~781,543. Repo: lmg-anon/vntl-llama3-8b-v2-gguf

Hugging Face GGUF · downloads ~297,721. Repo: hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF

Hugging Face GGUF · downloads ~298,243. Repo: bartowski/Meta-Llama-3.1-8B-Instruct-GGUF