NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Q4 GGUF download: mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-heretic-i1-GGUF - 24.52 GB on disk, read 2026-10-15. VRAM figures above are estimates; this is the actual file size.
Arena rating (LMArena)
Human preference wins from head-to-head chat battles
| Metric | Value |
|---|---|
| Overall arena rating | 1347.8 |
| Rank (overall) | #209 |
| Battle votes | 15,770 |
Overall rating published by LMArena on 2026-10-15 - a pairwise human-preference Elo across live chat battles; higher is better. Fetched 2026-10-19. Open-weights models compete head-to-head with proprietary ones here — no benchmark prompts, just what people pick.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| MMLU-Pro | 78.3 |
| HLE | 15.5 |
Additional scores from Hugging Face OpenEvals official leaderboards - updated 2026-10-19.
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-3-Nano-30B-A3B-BF16New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is a 31.6B-parameter other model from nvidia. At Q4_K_M it needs roughly 18 GB of VRAM, placing it in the 12-24gb hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 31.6B |
| Context length | 262K tokens |
| License | other |
| Modalities | text |
| Released | 2025-12-04 |
| Weights | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~18 GB | RTX 3090, RTX 4090 |
| Q5_K_M | ~22 GB | RTX 3090, RTX 4090 |
| Q8_0 | ~34 GB | RTX 6000 Ada, dual RTX 3090 |
| FP16 | ~63 GB | A100 80GB, H100 |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Popularity
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 has 1,645,889 downloads in the last month on HuggingFace and 750 likes.
Frequently asked
Quick answers to common questions
How much VRAM does NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 need?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with 31.6B parameters needs approximately 18 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 better than other nvidia models?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 has 31.6B parameters with 262,144 context - a strong choice for general use.
What license is NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 under?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is released under the other license, making it suitable for most commercial and personal projects.
What hardware runs NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 well?
With 31.6B parameters, NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 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-3-Nano-30B-A3B-BF16?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~22 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can NVIDIA-Nemotron-3-Nano-30B-A3B-BF16's context window handle?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 supports a 262,144-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-3-Nano-30B-A3B-BF16?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 competes with other 16B–47B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec