All AI models · LLM benchmarks · Methodology

NVIDIA

Nemotron 3 Nano 30B A3B FP8

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

Model facts

Context window
1M tokens
Maximum output
262K tokens
Cheapest paid input
$0.06 per 1M tokens
Cheapest paid output
$0.25 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 17.9 GiB, Q8_0 32.6 GiB, F16 60.2 GiB working memory.

Parameters
31.6 billion
Architecture
nemotronh
Model license
other

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.06 input / $0.25 output per 1M tokens

API providers

  • Infomaniak — model id nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8; $0.06 input / $0.25 output per 1M tokens; provider documentation