Open-Source NVIDIA Models

Match · Updated July 2026

The best open-weight NVIDIA model is Nemotron 3 Nano Omni (free) (14.9 intelligence) — downloadable from Hugging Face and self-hostable. Nemotron 3 Nano 30B A3B (7.4) and Nemotron 3.5 Content Safety (free) (—) round out the top three.

14.9Intelligence

FreeInput /M

256KContext

The best open-source AI models — open-weight, downloadable from Hugging Face and self-hostable — ranked by intelligence. Open-source alternatives to proprietary frontier models.

Frequently asked

What is the best open-source NVIDIA model?

What's a good alternative to Nemotron 3 Nano Omni (free)?

Nemotron 3 Nano 30B A3B (7.4) is the closest alternative on this metric, followed by Nemotron 3.5 Content Safety (free) (—). See the full ranking above for the tradeoffs.

How many NVIDIA models are there?

modelgrep tracks 10 NVIDIA models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Nemotron 3 Nano Omni (free). 10 of them qualify for this ranking.

More NVIDIA rankings

NVIDIA: Smartest LLMs NVIDIA: Best LLMs for Coding NVIDIA: Best LLMs for Design & Frontend NVIDIA: Fastest LLMs NVIDIA: Lowest-Latency LLMs NVIDIA: Cheapest LLMs NVIDIA: Best Free LLMs NVIDIA: Best Reasoning LLMs NVIDIA: Best Vision LLMs NVIDIA: Best LLMs for Agents NVIDIA: Longest-Context LLMs NVIDIA: Best LLMs for Writing NVIDIA: Best LLMs for Math & Science NVIDIA: Best LLMs for RAG NVIDIA: Best LLMs for SQL & Data Analysis NVIDIA: Best LLMs for Roleplay NVIDIA: Best Uncensored LLMs

All rankings

Small & Fast LLMs Best Local LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Fastest LLMs Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Longest-Context LLMs Best LLMs for Writing Best LLMs for Math & Science Best LLMs for RAG Best LLMs for SQL & Data Analysis Best LLMs for Roleplay Best Uncensored LLMs