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 12 quants, from 2.0 GB (Q2_K) to 8.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
4B Thai OCR vision‑language model for documents
P110 ThaiOCR 4B is a 4.33 billion‑parameter vision‑language model fine‑tuned from Qwen3.5‑4B. It reads printed and handwritten Thai documents, tables, PDFs and scans, and can answer questions about the content without per‑template rules.
Good at
- reasoning
- tools
- vision
Limits
- No thinking enabled
- No per‑template rules
- Apache‑2.0 license
Best for
- plain OCR of Thai text
- structured extraction from tables
- question answering about documents
Who it’s for. Developed by Porsuk Rungarunsrisuk and fine‑tuned from Qwen3.5‑4B, this model is ideal for Thai and English document processing tasks that require vision‑language capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| F16 | 8.7 GB | 10.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (1.96 GB file, ~3.6 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (2.78 GB file, ~4.4 GB memory) is suitable. For 24 GB VRAM, Q5_K_M (3.16 GB file, ~4.8 GB memory) provides higher quality.
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: the best quant that fits is Q3_K_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 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 F16 (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.
If memory is tight, the smallest file is Q2_K at 2.0 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 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: Q2_K is 2.0 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, IQ4_XS is 2.6 GB, Q4_K_S is 2.6 GB and 6 more.
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 mradermacher/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 this model on 8 GB VRAM?
Yes, the Q2_K quant uses about 3.6 GB memory at 8k context, fitting within 8 GB VRAM.
Does it support vision?
Yes, it is a vision‑language model that can process images of documents.
What license does it use?
The model is released under the Apache‑2.0 license.