CanItRun Logocanitrun.

Nemotron 3 Nano 30B

Nemotron 3 Nano 30B needs roughly 18.4GB VRAM at Q4_K_M quantization (72.2GB at FP16). 59 GPUs we track can run it fully in VRAM at 8k context.

NVIDIA32B params3B active (MoE)1024k contextNVIDIACommercial use ok

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP1664.0 GB0.44 GB72.2 GB
Q832.0 GB0.44 GB36.3 GB
Q6_K24.0 GB0.44 GB27.4 GB
Q5_K_M20.0 GB0.44 GB22.9 GB
Q4_K_M16.0 GB0.44 GB18.4 GB
Q3_K_M12.8 GB0.44 GB14.8 GB
Q2_K9.6 GB0.44 GB11.2 GB

Benchmarks

Benchmarks for this model are not yet available on the Open LLM Leaderboard v2. This is common for recently released models. Check back soon.

GPUs that run Nemotron 3 Nano 30B natively (59)

Plus 3 GPUs that run it with CPU offload (slower)

Notes

Hybrid Mamba-Transformer MoE — 30B total / 3B active per token. Optimized for agentic workflows.

Hugging Face ↗Released 2025-12-01