> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server. # Large Language Models ## Docs - [Large Language Models (LLMs)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/overview.md): - [Llama](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/llama.md): - [Gemma](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/gemma.md): - [Qwen2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/qwen-2.md): - [Qwen2 MoE](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/qwen-2-mo-e.md): - [Qwen3](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/qwen-3.md): - [Qwen3 MoE](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/qwen-3-mo-e.md): - [Qwen3-Next](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/qwen-3-next.md): - [ERNIE 4.5](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ernie-4-5.md): - [DeepSeek](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/deep-seek.md): - [DeepSeek-V3](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/deep-seek-v-3.md): - [DeepSeek V4 Flash](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/deep-seek-v-4-flash.md): - [Mistral](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/mistral.md): - [Mixtral](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/mixtral.md): - [Ministral3 / Devstral](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ministral3-devstral.md): - [Phi](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/phi.md): - [Phi-3 / Phi-4](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/phi-3-phi-4.md): - [Phi-3-Small](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/phi-3-small.md): - [Nemotron / Minitron](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/nemotron-minitron.md): - [Nemotron-H](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/nemotron-h.md): - [Nemotron-Flash](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/nemotron-flash.md): - [Nemotron-Super (Llama-3.3-Nemotron-Super-49B)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/nemotron-super-llama-3-3-nemotron-super-49b.md): - [ChatGLM](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/chat-glm.md): - [GLM-4](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/glm-4.md): - [GLM-4 MoE (GLM-4.5 / GLM-4.7)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/glm-4-moe-glm-4-5-glm-4-7.md): - [GLM-5 / GLM-5.1 / GLM-5.2 (MoE + DSA)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/glm-5-moe-dsa.md): - [Granite](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/granite.md): - [Granite MoE](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/granite-mo-e.md): - [Bamba](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/bamba.md): - [OLMo](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ol-mo.md): - [OLMo2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ol-mo-2.md): - [OLMoE](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ol-mo-e.md): - [GPT-OSS](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/gpt-oss.md): - [GPT-2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/gpt-2.md): - [GPT-J](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/gpt-j.md): - [GPT-NeoX / Pythia](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/gpt-neox-pythia.md): - [StarCoder](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/star-coder.md): - [StarCoder2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/star-coder-2.md): - [Aquila / Aquila2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/aquila-aquila2.md): - [Baichuan / Baichuan2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/baichuan-baichuan2.md): - [Command-R](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/command-r.md): - [Falcon](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/falcon.md): - [EXAONE](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/exaone.md): - [InternLM](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/intern-lm.md): - [Jais](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/jais.md): - [MiniMax-M2](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/mini-max-m-2.md): - [MiniCPM](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/mini-cpm.md): - [Moonlight](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/moonlight.md): - [Seed (ByteDance)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/seed-byte-dance.md): - [Solar Pro](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/solar-pro.md): - [Orion](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/orion.md): - [StableLM](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/stable-lm.md): - [Step-3.5](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/step-3-5.md): - [GritLM](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/grit-lm.md): - [Hy3 (HunyuanLarge)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/hy-3-preview.md): - [Hy-MT2 (Hunyuan-MT2)](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/hy-mt-2.md): - [MiMo-V2-Flash](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/mi-mo-v-2-flash.md): - [Ling 2.0](https://docs.nvidia.com/nemo/automodel/v0.5/model-coverage/large-language-models/ling-2-0.md):