Task
Image Text To Text
L
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image Text To Text·nvidia· 1.2M· 181
transformers
other
8.7B params
license:otherregion:us
Llama Nemotron Nano VL is a leading document intelligence vision language model (VLMs) that enables the ability to query and summarize images from the physical or virtual world. Llama Nemotron Nano VL is deployable in the data center, cloud and at the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleave
# pull & run locally
pip install mlforge-sdk && mlforge pull nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
pip install mlforge-sdk && mlforge pull nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Model details
Provider
nvidia
Framework
transformers
Parameters
8.7B
Size
16 GB
License
other
Downloads
1.2M
Likes
181
Updated
2025-12-04
About nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Llama Nemotron Nano VL is a leading document intelligence vision language model (VLMs) that enables the ability to query and summarize images from the physical or virtual world. Llama Nemotron Nano VL is deployable in the data center, cloud and at the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance.