Llama-3.1-Nemotron-Nano-VL-8B-V1

Home/Models/nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1

nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1

kind: original
quant: bf16 (16-bit)
family: llama
modality: image-text-to-text
root model: nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
provider: nvidia
license: other
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,269,297
likes: 181
created: —
last modified: 2025-12-04T17:42:32+00:00 (2025)
huggingface: https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
tags: transformerssafetensorsnvidiaVLMllama3.1image-text-to-textlicense:otherendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	91.2	DocVQA val	medium	`\| DocVQA val \| 91.2% \|`
ChartQA	multimodal	86.3	ChartQA	medium	`\| ChartQA \| 86.3% \|`
MMMU	multimodal	48.2	MMMU Val with chatGPT as a judge	medium	`\| MMMU Val with chatGPT as a judge \| 48.2% \|`

none scraped.