NVIDIA NIM provides optimized inference for 190+ models on NVIDIA GPU infrastructure.
| Model |
|---|
gemma-7bgoogle/gemma-7b |
mistral-7b-instruct-v0.2mistralai/mistral-7b-instruct-v0.2 |
mistral-7b-instruct-v0.3mistralai/mistral-7b-instruct-v0.3 |
glm-5.1z-ai/glm-5.1 |
llama-4-maverick-17b-128e-instructOSSmeta/llama-4-maverick-17b-128e-instruct |
gemma-4-31b-itgoogle/gemma-4-31b-it |
llama-4-scout-17b-16e-instructOSSmeta/llama-4-scout-17b-16e-instruct |
qwen3.5-397b-a17bOSSqwen/qwen3.5-397b-a17b |
qwen3.5-122b-a10bOSSqwen/qwen3.5-122b-a10b |
llama-3.3-70b-instructOSSmeta/llama-3.3-70b-instruct |