NVIDIA

Nemotron Nano v2 9B

8,9B

Parameters

6,1 Go

Q4_K_M file

≥ 7,6 Go

Recommended VRAM

131 072

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 7,6 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2025-08-12
Architecture: 56 layers · 8 KV heads · dimension 128
Attention: Hybrid: 4 of 56 layers use standard attention, the others a fixed-memory mechanism (Mamba, linear attention) — a very light cache.
Context cache (f16): ≈ 16 MB per 1,000 tokens · 0,5 Go for 32,768 tokens
GGUF file: bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF · nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf Download (6,1 Go)
Official repo: nvidia/NVIDIA-Nemotron-Nano-9B-v2

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.