N
Nemotron Nano 12B 2 VL (free)OPEN
Nemotron Nano 12B 2 VL (free) (NVIDIA): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for Nemotron Nano 12B 2 VL (free), measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Nemotron Nano 12B 2 VL (free) delivers 4.9 times more capability. Open weights also mean you can self-host it and pay nothing per token.
About this model
Nemotron Nano 12B 2 VL (free) is an open-weight AI model by NVIDIA. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Nemotron Nano 12B 2 VL (free)?
Nemotron Nano 12B 2 VL (free) is an AI language model from NVIDIA. It is open-weight: you can download it and run it on your own hardware, for free. It scores 9 on the Artificial Analysis intelligence index.
Is Nemotron Nano 12B 2 VL (free) free?
The weights are free and open — you can self-host Nemotron Nano 12B 2 VL (free) and pay nothing per token. If you prefer a hosted API, list prices are Free per million input tokens and Free per million output tokens.
What is Nemotron Nano 12B 2 VL (free) good at?
Independent benchmarks from Artificial Analysis give it GPQA 57.2%, MMLU-Pro 75.9%, Humanity's Last Exam 5.3%, Long Context Reasoning 40%, LiveCodeBench 69.4%, SciCode 26.2%, AIME 2025 75%, IFBench 31.9%, τ²-Bench 21.3%, Terminal-Bench Hard 4.5%. It is particularly used for mathematical reasoning.
How fast is Nemotron Nano 12B 2 VL (free)?
It generates about 75.8 tokens per second, with a median 3.34s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Nemotron Nano 12B 2 VL (free)?
Yes. Nemotron Nano 12B 2 VL (free) has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.