NVIDIA

NVIDIA Nemotron Nano 3 30B

Generally availableOpen weights262K contextReasoning

Summary

NVIDIA Nemotron Nano 3 30B is an open-weight language model from NVIDIA, released on 15 Dec 2025. It accepts text and generates text, with a 262K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.05 per million input tokens and $0.20 per million output tokens (Novita AI), across 3 providers we track.

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperNVIDIA
Release date15 Dec 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensenvidia-nemotron-open-model-license [Hugging Face]
Parameters31.6B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output8K tokens [models.dev]
Knowledge cutoff25 Jun 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facenvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 [Hugging Face]

NVIDIA Nemotron Nano 3 30B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Novita AI
nvidia/nemotron-3-nano-30b-a3b
$0.05$0.20–262Kmodels.dev, 18 Nov 2026
Amazon Bedrock
nvidia.nemotron-nano-3-30b
$0.06$0.24–262Kmodels.dev, 18 Nov 2026
OpenRouter
nvidia/nemotron-3-nano-30b-a3b
$0.06$0.24$0.01262KOpenRouter, 18 Nov 2026

Running NVIDIA Nemotron Nano 3 30B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)19 GB20 GB20 GB
Q8_0 (8-bit)34 GB34 GB35 GB
FP16 / BF16 (16-bit)63 GB64 GB64 GB

At 4-bit with an 8K conversation, NVIDIA Nemotron Nano 3 30B needs about 20 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of NVIDIA Nemotron Nano 3 30B?

NVIDIA Nemotron Nano 3 30B has a context window of 262,144 tokens (262K) and can generate up to 8,192 tokens in a single response, according to models.dev.

How much does the NVIDIA Nemotron Nano 3 30B API cost?

NVIDIA Nemotron Nano 3 30B is listed from $0.05 per million input tokens and $0.20 per million output tokens (Novita AI). Prices last verified 18 Nov 2026.

Is NVIDIA Nemotron Nano 3 30B open source?

NVIDIA Nemotron Nano 3 30B is an open-weight model: its weights are published on Hugging Face as nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 under the nvidia-nemotron-open-model-license license. Check the license terms before commercial use.

When was NVIDIA Nemotron Nano 3 30B released?

NVIDIA released NVIDIA Nemotron Nano 3 30B on 15 Dec 2025, according to models.dev.

Which providers offer NVIDIA Nemotron Nano 3 30B?

We track NVIDIA Nemotron Nano 3 30B on 3 providers: Novita AI, Amazon Bedrock, OpenRouter.

How much VRAM does NVIDIA Nemotron Nano 3 30B need?

About 20 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 34 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Ministral 3 8BMistral AI2 Dec 2025262K$0.15$0.15Open
Qwen/Qwen3.5-9BAlibaba (Qwen)23 Feb 2026262K$0.10$0.15Open
Ministral 14BMistral AI2 Dec 2025262K$0.20$0.20Open
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
Jamba MiniAI21 Labs8 Jan 2026256K$0.20$0.40Open
Gemma 4 26B A4B ITGoogle DeepMind2 Apr 2026262K$0.07$0.30Open

Change history

  • Name changed from Nemotron 3 Nano 30B A3B to NVIDIA Nemotron Nano 3 30B
  • Max output changed from 33K to 8K
  • Name changed from NVIDIA Nemotron Nano 3 30B to Nemotron 3 Nano 30B A3B
  • Max output changed from 8K to 33K
  • Max output changed from 33K to 8K
  • Name changed from Nemotron 3 Nano 30B A3B to NVIDIA Nemotron Nano 3 30B
  • Name changed from NVIDIA Nemotron Nano 3 30B to Nemotron 3 Nano 30B A3B
  • Max output changed from 8K to 33K
  • Name changed from Nemotron 3 Nano 30B A3B to NVIDIA Nemotron Nano 3 30B
  • Max output changed from 262K to 8K
  • Tool calling changed from no to yes
  • No longer listed on vercel
  • Tool calling changed from yes to no
  • Max output changed from 236K to 262K
  • Max output changed from 262K to 236K
  • Tool calling changed from no to yes
  • Tool calling changed from yes to no
  • Max output changed from 33K to 262K
  • Max output changed from 262K to 33K
  • Tool calling changed from no to yes
  • Max output changed from 236K to 262K
  • Tool calling changed from yes to no
  • Max output changed from 262K to 236K
  • Tool calling changed from no to yes
  • Tool calling changed from yes to no

Sources