Last refreshed 2026-05-14. Next refresh: weekly.
Why use Nemotron 3 Nano on NVIDIA NIM?
NVIDIA NIM offers Nemotron 3 Nano with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: nvidia/nemotron-3-nano-30b-a3bModel ID
nvidia/nemotron-3-nano-30b-a3bRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
nvidia/nemotron-3-nano-30b-a3b.Gotchas
- Use provider model ID "nvidia/nemotron-3-nano-30b-a3b", not the LLMReference slug "nemotron-3-nano".
Capabilities
JSON / Tool use
About Nemotron 3 Nano
NVIDIA's lightweight 3.97B parameter model optimized for edge deployment with FP8 quantization (W8A8 mixed precision). Designed for agentic AI applications including gaming NPCs, local voice assistants, and IoT automation. Supports instruction following, tool use, and hallucination avoidance. Strong performance on BFCL, IFBench, IFEval, HaluEval, RULER, Tau2, AIME25, MATH500, GPQA-D, and LiveCodeBench.
Model Specs
Released2025-12-15
Parameters3.97B
Context256k
ArchitectureMixture of Experts