Typhoon Ocr 3b needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.8 GB (IQ1_S) to 2.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Typhoon Ocr 3b – a vision‑enabled document parsing model
Typhoon Ocr 3b is a 3.09 billion parameter vision model based on qwen2vl. It is trained on 128000 context tokens and licensed under apache‑2.0. The model specializes in parsing Thai and English documents with structured output.
Good at
- Thai and English document OCR
- Structured table extraction
- Figure and diagram interpretation
Limits
- No vision support in non‑vision builds
- Requires specific prompt for correct operation
- Large context needed for full documents
Best for
- Financial report extraction
- Academic paper summarization
- Government form processing
Who it’s for. Developers building document‑centric applications that need accurate Thai and English OCR. The model is suitable for local deployment via GGUF files and llama.cpp or LM Studio, though accuracy may vary with those runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.8 GB | 1.6 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XS | 1.0 GB | 1.8 GB | Fits | Get file → | |
| IQ2_S | 1.1 GB | 1.9 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q2_K_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 1.3 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XS | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_NL | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM use IQ1_S (0.79 GB, 1.6 GB memory at 8k context) or IQ1_M (0.85 GB, 1.7 GB). For 12 GB VRAM use Q4_K_M (1.93 GB, 2.7 GB) or Q5_K_M (2.22 GB, 3 GB). Higher quants increase accuracy but require more memory.
What GPU do you need for Typhoon Ocr 3b?
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 Q6_K (2.5 GB file, about 3.3 GB in use).
Which Typhoon Ocr 3b quant should you choose?
Q4_K_M is the usual starting point for Typhoon Ocr 3b: it balances file size and quality well. Here it is a 1.9 GB file.
If memory is tight, the smallest file is IQ1_S at 0.8 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 Typhoon Ocr 3b
How much VRAM does Typhoon Ocr 3b need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Typhoon Ocr 3b on an 8 GB GPU?
Yes, with Q6_K: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Typhoon Ocr 3b GGUF?
It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.1 GB, IQ2_M is 1.1 GB and 18 more.
What context length does Typhoon Ocr 3b support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download Typhoon Ocr 3b GGUF?
The files are on Hugging Face in the mradermacher/typhoon-ocr-3b-i1-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 Typhoon Ocr 3b 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 Typhoon Ocr 3b on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quant files. They require approximately 1.6–1.7 GB memory at 8k context.
Does the model support other languages besides Thai and English?
The model is specifically built for Thai and English; other languages are not guaranteed to work.
Is there a vision‑only build available?
The GGUF files are vision‑enabled; mmproj files are not provided in this release.