// NVIDIA Nemotron · Vision-language
NVIDIA-Nemotron-Nano-12B-v2-VL-BF16: VRAM & local deployment
13.2B parameters. About 9.5 GB at 4-bit and 29.7 GB at BF16 with one 8K-token request.
released 2025-10-21licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | NVIDIA · nvidia |
|---|---|
| Family / series | NVIDIA Nemotron · NVIDIA-Nemotron-Nano-VL |
| Type | Vision-language (image-text-to-text) |
| Parameters | 13.2B Source: counted from official safetensors weights |
| Context length | 128K tokens (131,072)max_position_embeddings in config.json |
| Architecture | 62 layers (6 full-attention) · GQA+HYBRID |
| Released weights | BF16 · 26.4 GBdownload |
| Licence | nvidia-open-model-license · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2025-10-21 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 26.4 GB | 29.7 GB | 30.3 GB | 32.7 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 14.0 GB | 16.1 GB | 16.7 GB | 19.1 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 8.0 GB | 9.5 GB | 10.1 GB | 12.5 GB | 12GB GPU | Mac 16GB |
KV cache per request: 8K 0.2 GB · 32K 0.8 GB · 128K 3.2 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
- TensorRT-LLM — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from nvidia.
05Other NVIDIA Nemotron models
All 62 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | 3.98B | 3.6 GB | 2026-10-16 |
| Nemotron-3.5-Rerank-8B-BF16 | 8.38B | 6.1 GB | 2026-10-15 |
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 | 124.5B / 12B | 83.5 GB | 2026-10-12 |
| NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 | 74.9B / 9B | 50.4 GB | 2026-10-09 |
| Nemotron-3.5-Embed-1B-BF16 | 1.55B | 1.5 GB | 2026-10-07 |
| Nemotron-3.5-Embed-8B-BF16 | 8.38B | 6.1 GB | 2026-10-07 |
| Nemotron-3.5-Parse | 631M | 1.1 GB | 2026-09-03 |
| Nemotron-3-Labs-Ultra-Math-RL | 550B / 55B | 367 GB | 2026-09-02 |
06Sources
Data checked 2026-08-25. Parameters, context and licence are copied from the official repository; memory figures are our estimates.