NVIDIA-Nemotron-Nano-9B-v2
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
14.8
AA Index
Coding
8.3
AA Index
Agentic
9.4
AA Index
Math
69.7
AA Index
Intelligence Index - NVIDIA-Nemotron-Nano-9B-v2 vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Math Index comparison
Benchmark data from Artificial Analysis · updated 2026-06-07.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| MMLUPRO | 74.2 |
| GPQA | 57 |
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve nvidia/NVIDIA-Nemotron-Nano-9B-v2New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
NVIDIA-Nemotron-Nano-9B-v2
NVIDIA-Nemotron-Nano-9B-v2 is a 8.9B-parameter other model from nvidia. It scores 13.2 on the Artificial Analysis Intelligence Index (coding 7.5). At Q4_K_M it needs roughly 5 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 8.9B |
| Context length | 131K tokens |
| License | other |
| Modalities | text |
| Released | 2025-08-12 |
| Weights | nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
Benchmarks
Artificial Analysis Intelligence Index - NVIDIA-Nemotron-Nano-9B-v2 vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 13.2 | 7.5 | 55.7 |
| GPT-5.5 (xhigh) | 60.2 | 59.1 | 93.5 |
| Claude Opus 4.8 (max) | 61.4 | 56.7 | 92 |
| Gemini 3.1 Pro Preview | 57.2 | 55.5 | 94.1 |
| Grok 4.3 (high) | 53.2 | 41 | 90.1 |
Source: Artificial Analysis (2026-06-04).
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~5 GB | RTX 4060, RTX 3060 8GB |
| Q5_K_M | ~6 GB | RTX 4060, RTX 3060 8GB |
| Q8_0 | ~10 GB | RTX 3060 12GB, RTX 4070 |
| FP16 | ~18 GB | RTX 3090, RTX 4090 |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve nvidia/NVIDIA-Nemotron-Nano-9B-v2Popularity
NVIDIA-Nemotron-Nano-9B-v2 has 469,996 downloads in the last month on HuggingFace and 493 likes.
Frequently asked
Quick answers to common questions
How much VRAM does NVIDIA-Nemotron-Nano-9B-v2 need?
NVIDIA-Nemotron-Nano-9B-v2 with 8.9B parameters needs approximately 5 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is NVIDIA-Nemotron-Nano-9B-v2 better than other nvidia models?
NVIDIA-Nemotron-Nano-9B-v2 has 8.9B parameters with 131,072 context - a strong choice for general use.
What license is NVIDIA-Nemotron-Nano-9B-v2 under?
NVIDIA-Nemotron-Nano-9B-v2 is released under the other license, making it suitable for most commercial and personal projects.
What hardware runs NVIDIA-Nemotron-Nano-9B-v2 well?
With 8.9B parameters, NVIDIA-Nemotron-Nano-9B-v2 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for NVIDIA-Nemotron-Nano-9B-v2?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~6 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can NVIDIA-Nemotron-Nano-9B-v2's context window handle?
NVIDIA-Nemotron-Nano-9B-v2 supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with NVIDIA-Nemotron-Nano-9B-v2?
NVIDIA-Nemotron-Nano-9B-v2 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec
Similar by size
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.