TH

P110-ThaiOCR-4B

ThaiocrGGUF by PorsukRUpdated 2026-10-24
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.8 GB
Quick answer

P110-ThaiOCR-4B needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.8 GB (Q4_K_M) to 8.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

4B vision‑language model for Thai document OCR

P110‑ThaiOCR‑4B is a 4.33B parameter model fine‑tuned from Qwen3.5‑4B. It reads printed and handwritten Thai documents, tables, forms and PDFs into plain text or structured output. The model can also answer questions about a document without per‑template rules.

Good at

  • Thai OCR transcription
  • Document question answering
  • Structured data extraction

Limits

  • No vision support without mmproj file
  • Requires 8k context for full memory estimate
  • License is Apache‑2.0

Best for

  • Transcribing Thai PDFs
  • Extracting tables from scanned forms
  • Answering document‑specific queries

Who it’s for. Developers building Thai document processing tools. Researchers needing a lightweight OCR model. Teams that require open‑source licensing for Thai language content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q8_04.6 GB 6.2 GB
Fits Get file →
BF168.7 GB 10.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (2.78 GB file, ~4.4 GB memory). For 12 GB VRAM use Q8_0 (4.61 GB file, ~6.2 GB memory). BF16 needs ~10.3 GB memory and 8.67 GB file size.

What GPU do you need for P110-ThaiOCR-4B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.8 GB file, about 4.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.7 GB file, about 10.3 GB in use).

Which P110-ThaiOCR-4B quant should you choose?

Q4_K_M is the usual starting point for P110-ThaiOCR-4B: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.6 GB, about 1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byPorsukR
FamilyThaiocr
Licenseapache-2.0
Downloads (HF)814
Last updated2026-10-24

Frequently asked questions about P110-ThaiOCR-4B

How much VRAM does P110-ThaiOCR-4B need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 P110-ThaiOCR-4B on an 8 GB GPU?

Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of P110-ThaiOCR-4B GGUF?

It depends on the quant: Q4_K_M is 2.8 GB, Q8_0 is 4.6 GB, BF16 is 8.7 GB.

What context length does P110-ThaiOCR-4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download P110-ThaiOCR-4B GGUF?

The files are on Hugging Face in the PorsukR/P110-ThaiOCR-4B-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 P110-ThaiOCR-4B 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 P110‑ThaiOCR‑4B on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 4.4 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision?

Vision is supported only when the mmproj-P110‑ThaiOCR‑4B‑F16.gguf file is present; otherwise it is text‑only.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of P110-ThaiOCR-4B

Similar models

Browse all →

More from PorsukR

All by PorsukR →

More Thaiocr models

All Thaiocr →

Other small models

All small models →