Skip to content
Local AI Wizard
Your machine
Theme

NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

NVIDIA · nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

Weights license: Publisher terms: NVIDIA Open Model License · code and components may use other terms

Reported by the publisher10 resultsNVIDIA's model card · read 2026-10-25 · not ranked · see them
Memory needed~10 GBQ4 weights + working room, before the machine's reserve
Parameters13.2 BHub safetensors total
Repository updated2026-08-25A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

10 results · NVIDIA's model card · read 2026-10-25
MMMU
68
MathVista
76.9
AI2D
87.11
OCRBenchv2
62.0
OCRBench
85.6
OCR-Reasoning
36.4
ChartQA
89.72
DocVQA
94.39
Every reported result10
Video-MME w/o sub
65.9
Vision Average
74.0

Values as printed on the card, with the publisher's own settings (card section: Self-Sourced Synthetic Data › Evaluation Datasets:). Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 90

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 90

Within memory, outside the fast part 26

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 26

One memory tier short 3

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

NVIDIA released NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 on 2025-10-28: a vision-language model that answers about images, with 13.2B parameters on the Hugging Face count and the Publisher terms: NVIDIA Open Model License license. Languages the publisher declares: en.

Check first

License: commercial use allowed. At Q4 the weights load about 9.9 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Transformers · model card · Single Image Inference
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer

# Load model and processor
model_path = "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16"  # Or use a local path
device = "cuda:0"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    device_map=device,
    torch_dtype=torch.bfloat16
).eval()
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

# Load image
image = Image.open("path/to/your/image.jpg")

# Prepare messages
messages = [
    {"role": "system", "content": "/no_think"},
    {
        "role": "user",
        "content": [
            {"type": "image", "image": ""},
            {"type": "text", "text": "Describe the image."},
        ],
    }
]

# Generate prompt and process inputs
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[prompt], images=[image], return_tensors="pt").to(device)

# Generate output
generated_ids = model.generate(
    pixel_values=inputs.pixel_values,
    input_ids=inputs.input_ids,
    attention_mask=inputs.attention_mask,
    max_new_tokens=1024,
    do_sample=False,
    eos_token_id=tokenizer.eos_token_id,
)

# Decode output
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False
)[0]
print(output_text)
vLLM · model card · Inference with vLLM
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
image-text-to-text
Library in source
transformers
Weight license
Publisher terms: NVIDIA Open Model LicenseNVIDIA Open Model License Agreement (linked from the model card) · read 2026-10-18source
Commercial use
Allowed NVIDIA Open Model License Agreement, last modified 2025-10-24 (copy shipped in NVIDIA's NVlabs/GRAIL repository) · read 2026-10-18license text
Languages
en Publisher's statement · read 2026-10-18source
Released
NVIDIA Nemotron Nano 12B v2 VL model card, Release Date: Hugging Face [October 28th, 2025] · read 2026-10-18source
Every stored field12 fields
Revision checked
ca9543b126e8bf3176916d3d305ccc415f89fd4d
Library
transformers
Hub task tag
image-text-to-text
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Hub parameter count
13,181,860,358safetensors.total
Repository created
2025-10-21creation is not the model's release
Repository updated
2026-08-25a commit is not a release date
Hub downloads (30 days) · likes
15,330 · 96this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tagsHub overview and file listing · read 2026-10-18
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.