Tools,

HunyuanOCR tested on a Mac in llama.cpp

1,951

of 1,955 words on a 10-page scan

Get the script

Version 1.0 beat 1.5 on our scan

Tencent's 1B model read 10 proofread book pages on an M5 Max Mac.

Words found of 1,955, and time for 10 pages
Way Words Time
1.0 Q8_0, our script, 1,280 px 1,951 46 s
1.0, full size 1,950 95 s
1.0, 1,280 px 1,949 24 s
1.5, full size 1,945 121 s
1.5, 1,280 px 1,942 24 s

Half of 1.5's 10 misses are stray spaces, like " Keep for "Keep. Three are -- for a dash.

1.0 at full size kept line-end hyphens (educa-tion) and read drawled as drewled.

Shrink the page: 4 to 5 times faster

The model reads the page as tokens before it writes. That takes most of the time.

Input tokens per page (image and prompt)
Page 1.0 1.5
1,920 px wide, full size 4,128 to 4,208 5,721 to 5,904
1,280 px on the long side 1,088 to 1,128 1,088 to 1,128
Largest image it reads 4.2 megapixels 16.8 megapixels

At 1,280 px both took about 2.4 s a page and lost at most 3 words.

DFlash did not help here

1.5 ships DFlash, a draft model, to write faster. The same text took 142 s, not 121 s.

Mean time per full page, version 1.5
Step Plain DFlash
Reading the image 10.4 s 13.4 s
Writing the text 1.4 s 0.6 s

Writing got faster, but reading got slower, and reading is most of a page. Tencent's guide reports the same.

Run it on a Mac

brew install poppler
curl -LO https://github.com/ggml-org/llama.cpp/releases/download/b12470/llama-b12470-bin-macos-arm64.tar.gz
tar xzf llama-b12470-bin-macos-arm64.tar.gz
export PATH="$PWD/llama-b12470:$PATH"
curl -LO https://huggingface.co/ggml-org/HunyuanOCR-GGUF/resolve/main/HunyuanOCR-Q8_0.gguf
curl -LO https://huggingface.co/ggml-org/HunyuanOCR-GGUF/resolve/main/mmproj-HunyuanOCR-Q8_0.gguf
curl -LO https://brasspage.com/hunyuan-ocr/hyocr.sh
sh hyocr.sh scan.pdf > book.md

hyocr.sh reads each PDF page as a 1,280 px JPEG.

The prompt is Tencent's own, in Chinese. An English prompt found 1,940 on 1.5.

The ggml-org files are version 1.0. For 1.5, convert Tencent's weights with convert_hf_to_gguf.py from the llama.cpp source, then change the two file names in hyocr.sh.

The license stops at three borders

I read the Tencent Hunyuan Community License in full first. This is not legal advice.

Near the top of our list

Same 10 pages, words found of 1,955
Tool Words Time
MiniCPM-OCR 1.0, llama.cpp 1,954 16 s
olmOCR-2 7B 1,954 77 s
LightOnOCR-2 1B 1,954 72 s
HunyuanOCR 1.0, our script 1,951 46 s
Unlimited-OCR, llama.cpp 1,949 43 s
HunyuanOCR 1.5, full size 1,945 121 s
Our Actor's code 1,879 44 s
Tesseract 5.5.4 1,878 36 s

Times are rough: other rows ran on earlier days, and a second 1.5 run took 156 s.

How we ran it
  • A Mac with Apple M5 Max. llama.cpp b12470 from GitHub, Metal, llama-server with the flags of Tencent's guide, one page per request, temperature 0.
  • 1.0: the ggml-org GGUF files (bf16 and Q8_0). 1.5: Tencent's weights, converted to f16 here, and a Q8_0 made from that. Q8_0 cost 1.0 one word and changed nothing for 1.5.
  • Every run at low priority (nice and background QoS), one at a time, while other jobs ran on the Mac.
  • The scan: 10 proofread pages from two public domain books on Wikisource, 1,955 words, the same JPEGs as our earlier tests.
  • Score: true words found in order. Extra text, like running heads, costs nothing.
  • Our script's time includes loading the model for each page. The other rows load it once.

Scanned pages to text, no install

Run it yourself. Our Apify Actor turns a scanned PDF into Markdown or text. $0.006 a scanned page. Its code found 1,879 of these 1,955 words.

Try the Actor

Or send us the scan. Tack, our AI, does the job for $29, up to 50 pages. First page free.

Get one page free

Questions people ask

What is HunyuanOCR?

An OCR vision model from Tencent with about 1 billion parameters. It reads a page image and writes Markdown. Version 1.5 came out in 2026; version 1.0 stays in the same Hugging Face repo.

Does HunyuanOCR run on a Mac?

Yes, in llama.cpp. Tencent's vLLM and transformers setups need an NVIDIA GPU, but its llama.cpp guide covers laptops. llama.cpp ran both versions on the Mac GPU.

Is HunyuanOCR 1.5 better than 1.0?

Not on our scan: at full size, 1.0 found 5 more words. Half of the newer version's misses were stray spaces next to quote marks.

Can I use HunyuanOCR in a business?

Outside the EU, the UK and South Korea, yes, under the Tencent Hunyuan Community License. Its output may not be used to improve other AI models. A company with over 100 million monthly users at the model's release needs a license from Tencent.

Can HunyuanOCR read a PDF?

Not directly in llama.cpp: it takes images. Our script turns each PDF page into a JPEG with pdftoppm, then reads the pages one at a time.