TY

Typhoon Ocr 3b

TyphoonGGUF by mradermacherUpdated 2026-01-15
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant1.3 GB
Quick answer

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 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Typhoon Ocr 3b – bilingual document parsing with vision

Typhoon Ocr 3b is a 3.09 billion‑parameter Qwen2VL model trained on 128000 context tokens. It parses Thai and English documents and outputs Markdown, HTML tables, and figure tags. The model is licensed under apache‑2.0.

Good at

  • Vision‑enabled OCR for Thai and English
  • Structured document extraction
  • Figure and layout analysis

Limits

  • No vision support in non‑vision prompts
  • Requires specific prompt to function
  • Large memory for higher quantizations

Best for

  • Financial report parsing
  • Academic paper extraction
  • Government form digitization

Who it’s for. Users needing accurate OCR on Thai and English documents. Ideal for developers building document‑processing pipelines who can supply the required prompt format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 2.1 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (file size 1.93 GB, estimated 2.7 GB memory). For 12 GB VRAM use Q5_K_M (file size 2.22 GB, estimated 3 GB memory). For 16 GB VRAM use Q6_K (file size 2.54 GB, estimated 3.3 GB 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).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 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.

The Q8_0 file is 3.3 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 1.3 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

Architectureqwen2vl
Parameters3.09B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyTyphoon
Licenseapache-2.0
Downloads (HF)806
Last updated2026-01-15

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 F16: the 6.2 GB file needs about 7.0 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: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 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-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, the Q4_K_M quant uses about 2.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support other languages besides Thai and English?

The model is specifically built for Thai and English; other languages are not guaranteed.

What prompt format is required?

The model requires a specific prompt; other prompts will not work correctly.

Other GGUFs of typhoon-ocr-3b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Typhoon models

All Typhoon →

Other tiny models

All tiny models →