Downloads · 30 days
295
19% of all-time downloads
LightOnOCR-2-1B-NVFP4
switzerchees/LightOnOCR-2-1B-NVFP4
LightOnOCR-2-1B-NVFP4 is a image-text-to-text model from switzerchees. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a NVFP4 variant of lightonai/LightOnOCR-2-1B, quantized with NVIDIA Model Optimizer PTQ for vLLM (modeloptfp4) compatibility.
All-time downloads
1.5K
Public
Parameters
812M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 99%
Parameter types
How the weights are stored.
BF16563M · 69%
Try a prompt
Base models
Model card
From the Hugging Face model README
LightOnOCR-2-1B-NVFP4
This is a NVFP4 variant of lightonai/LightOnOCR-2-1B, quantized with NVIDIA Model Optimizer PTQ for vLLM (modelopt_fp4) compatibility.
Upstream Model
- Original model card: lightonai/LightOnOCR-2-1B
- Original paper: LightOnOCR (arXiv:2601.14251)
- Original blog: LightOnOCR-2 announcement
Quantization Notes
- Quantization format: NVFP4
- Runtime target: vLLM with
quantization="modelopt_fp4" - Tooling: NVIDIA Model Optimizer
- Selective policy used for current vLLM compatibility:
- Quantized: language model and vision projection linear layers
- Kept BF16: vision encoder and vision patch merger
Usage (vLLM)
vllm serve switzerchees/LightOnOCR-2-1B-NVFP4 \
--quantization modelopt_fp4 \
--limit-mm-per-prompt '{"image": 1}' \
--mm-processor-cache-gb 0 \
--no-enable-prefix-caching
License
This derivative keeps the same license as the upstream model: Apache-2.0. See the original model card for upstream attribution and details: lightonai/LightOnOCR-2-1B
- Task
- Image-Text-to-Text
- Type
- mistral3
- License
- apache-2.0
- Created
- Feb 13, 2026
- Updated
- Feb 14, 2026