CO

Comma Lightonocr 3 0.8b

CommaGGUF by mradermacherUpdated 2026-10-13
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Comma 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: line‑by‑line medieval Latin OCR

Comma Lightonocr 3 0.8b is a Qwen3.5 vision‑language model fine‑tuned for CATMuS‑compliant transcription of medieval Latin manuscripts. It outputs one line of text per physical line in reading order, preserving graphemic details.

Good at

  • Line‑by‑line OCR
  • Preserves abbreviations
  • Handles medieval Latin scripts

Limits

  • No vision support beyond OCR
  • Limited to 262144 context tokens
  • Apache‑2.0 license restricts commercial use

Best for

  • Transcribing medieval manuscripts
  • Digitising historical documents
  • Creating searchable text archives

Who it’s for. Researchers and archivists needing accurate, line‑by‑line OCR of medieval Latin texts. The model is suitable for academic projects and digital humanities workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.53 GB, 1.4 GB memory) or Q5_K_M (0.58 GB, 1.5 GB memory) are recommended. For 4 GB VRAM, Q3_K_M (0.47 GB, 1.4 GB memory) or Q3_K_S (0.44 GB, 1.3 GB memory) provide a balance of size and performance. Higher‑quality F16 (1.52 GB, 2.4 GB memory) offers best accuracy if memory allows.

What GPU do you need for Comma 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 Comma Lightonocr 3 0.8b quant should you choose?

Q4_K_M is the usual starting point for Comma 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

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyComma
Licenseapache-2.0
Downloads (HF)755
Last updated2026-10-13

Frequently asked questions about Comma Lightonocr 3 0.8b

How much VRAM does Comma 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 Comma 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 Comma 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 Comma 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 Comma Lightonocr 3 0.8b GGUF?

The files are on Hugging Face in the mradermacher/comma-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 Comma 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 this model on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_M quantizations; they require about 1.4–1.5 GB VRAM at 8k context.

Does the model support vision tasks other than OCR?

No, it is fine‑tuned specifically for OCR; it does not support general vision tasks.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use with attribution.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Comma models

All Comma →

Other tiny models

All tiny models →