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

Home/Models/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

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

kind: original
quant: bf16 (16-bit)
family: nemotron
modality: image-text-to-text
root model: nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16
provider: nvidia
license: other
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 176,843
likes: 88
created: —
last modified: 2025-12-02T18:50:47+00:00 (2025)
huggingface: https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16
tags: transformerssafetensorsnvidiaVLMimage-text-to-textconversationalarxiv:2501.14818arxiv:2511.03929license:otherendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	94.39	DocVQA	medium	`\| DocVQA \| 94.39 \|`
ChartQA	multimodal	89.72	ChartQA	medium	`\| ChartQA \| 89.72 \|`
MathVista	multimodal	76.9	MathVista*	medium	`\| MathVista* \| 76.9 \|`
MMMU	multimodal	68.0	MMMU*	medium	`\| MMMU* \| 68 \|`

none scraped.