LightOnOCR 3 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
LightOnOCR 3 0.8B – lightweight OCR with vision and grounding
LightOnOCR 3 0.8B is a 0.752 billion‑parameter model built on the Qwen3.5 vision‑language architecture. It supports transcription, grounding, and visual understanding of tables, charts, and images. The model is released under Apache 2.0 for research and commercial use.
Good at
- Transcription of full page text
- Grounding with bounding boxes and labels
- Visual description of images and charts
Limits
- No language support listed
- Requires vision input only
- No explicit context length limit beyond 262144 tokens
Best for
- OCR of receipts and forms
- Document layout analysis
- Extracting data from charts
Who it’s for. Developers building document understanding pipelines who need a single, easy‑to‑deploy model. Researchers and businesses that require OCR with bounding box and visual description capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| F16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q4_K_S (0.53 GB or 0.51 GB). For 4 GB VRAM, use Q3_K_M or Q3_K_S (0.47 GB or 0.44 GB). For 2 GB VRAM, use Q2_K (0.42 GB). Memory estimates are approximate.
What GPU do you need for LightOnOCR 3 0.8B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (1.5 GB file, about 2.4 GB in use).
Which LightOnOCR 3 0.8B quant should you choose?
Q4_K_M is the usual starting point for LightOnOCR 3 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LightOnOCR 3 0.8B
How much VRAM does LightOnOCR 3 0.8B need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LightOnOCR 3 0.8B on an 8 GB GPU?
Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LightOnOCR 3 0.8B GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.
What context length does LightOnOCR 3 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download LightOnOCR 3 0.8B GGUF?
The files are on Hugging Face in the mradermacher/LightOnOCR-3-0.8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LightOnOCR 3 0.8B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LightOnOCR 3 0.8B on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_S quantizations, which are 0.53 GB and 0.51 GB respectively and require about 1.4 GB of VRAM at 8k context.
Does the model support multiple languages?
No language list is provided; the model is primarily focused on vision tasks.
Is there a vision-only mode?
The model is vision‑enabled and can be called with an empty prompt for transcription or with a grounding prompt for visual features.