HU

HunyuanOCR

HunyuanocrGGUF by mradermacherUpdated 2026-10-28
Download on Hugging Face
Parameters539M
Context32K
Layers24
Architecturehunyuan-dense
Smallest quant0.3 GB
Quick answer

HunyuanOCR needs about 1.7 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q2_K) to 1.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

HunyuanOCR – lightweight OCR vision‑language model

HunyuanOCR is a lightweight, end‑to‑end OCR‑specialized vision‑language model. It unifies document parsing, text spotting, information extraction, and text‑image translation. The model supports CPU, consumer‑GPU, and laptop deployment via llama.cpp.

Good at

  • OCR on dense documents
  • Long autoregressive decoding with DFlash
  • Vision‑language tasks

Limits

  • No vision support beyond OCR
  • Limited to 32768 context tokens
  • License is other

Best for

  • Document parsing
  • Text spotting
  • Information extraction

Who it’s for. Developers needing an OCR‑focused VLM that can run on consumer hardware. Ideal for applications requiring fast, end‑to‑end text extraction from images.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.6 GB
Fits Get file →
Q3_K_S0.3 GB 1.6 GB
Fits Get file →
Q3_K_M0.3 GB 1.6 GB
Fits Get file →
Q3_K_L0.3 GB 1.6 GB
Fits Get file →
IQ4_XS0.3 GB 1.6 GB
Fits Get file →
Q4_K_S0.3 GB 1.6 GB
Fits Get file →
Q4_K_M0.4 GB 1.7 GB
Fits Get file →
Q5_K_S0.4 GB 1.7 GB
Fits Get file →
Q5_K_M0.4 GB 1.7 GB
Fits Get file →
Q6_K0.4 GB 1.8 GB
Fits Get file →
Q8_00.6 GB 1.9 GB
Fits Get file →
F161.1 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.35 GB file, 1.7 GB memory at 8k context). For 4 GB VRAM, use Q2_K (0.26 GB file, 1.6 GB memory). For higher fidelity, choose Q5_K_M (0.4 GB file, 1.7 GB memory).

What GPU do you need for HunyuanOCR?

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 (1.1 GB file, about 2.4 GB in use).

Which HunyuanOCR quant should you choose?

Q4_K_M is the usual starting point for HunyuanOCR: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.6 GB, about 1.6 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 0.3 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

Architecturehunyuan-dense
Parameters539M
Layers24
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
Licenseother
Downloads (HF)1,370
Last updated2026-10-28

Frequently asked questions about HunyuanOCR

How much VRAM does HunyuanOCR need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.4 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 HunyuanOCR on an 8 GB GPU?

Yes, with F16: the 1.1 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 HunyuanOCR GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.3 GB, Q3_K_L is 0.3 GB, IQ4_XS is 0.3 GB, Q4_K_S is 0.3 GB and 6 more.

What context length does HunyuanOCR support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download HunyuanOCR GGUF?

The files are on Hugging Face in the mradermacher/HunyuanOCR-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 HunyuanOCR use?

Hugging Face lists the license as other. 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 HunyuanOCR on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 1.7 GB memory at 8k context, which fits within 8 GB VRAM.

Does HunyuanOCR support multi‑image text‑centric QA?

Yes, the model is designed for multi‑image text‑centric QA as part of its upgraded training recipe.

What is the maximum context length of HunyuanOCR?

The model was trained with 32768 context tokens.

Other GGUFs of HunyuanOCR

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hunyuanocr models

All Hunyuanocr →

Other tiny models

All tiny models →