GLM-OCR
Hacker ApprovedRanked 3 of 11 OCR models by recommenders
Free 0.9 billion parameter OCR model that runs fast on laptops and CPUs with good results on complex documents. Caveat: connection timeouts on large PDFs.
Free 0.9 billion parameter OCR model that runs fast on laptops and CPUs with good results on complex documents. Caveat: connection timeouts on large PDFs.
20 people gave an opinion
- recommend it
- 16
- criticize it
- 4
- approval share
- 80%
Recommended in 7 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 16 people recommend itNeeds 10 or more, met.
- 4 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Fast, small model with good speed
“this looks really cool and, given I'm looking for OCR at the moment, I'm pretty interested”
Comment from 11 Feb 2026 in “GLM-OCR: Accurate × Fast × Comprehensive” “Perhaps the greatest benefit of GLM-OCR is speed: it's only a 0.9 billion parameter model”
Comment from 14 Mar 2026 in “Can I Run AI locally?” “this is already a small and fast model when hosted via MLX on macOS”
Comment from 3 Apr 2026 in “Google releases Gemma 4 open models” - Comment from 6 Apr 2026 in “Show HN: I Built Paul Graham's Intellectual Captcha Idea”
- Comment from 24 Aug 2026 in “OCR It – pull text out of un-copyable documents for your LLM”
- Comment from 24 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing”
Runs locally on laptops and CPUs
“It has good layout recognition quality, good text recognition quality, and they actually tested it on Apple Silicon laptops.”
Comment from 13 Mar 2026 in “Can I Run AI locally?” “GLM-OCR does much better than Claude, can be running on pretty miserly hardware locally, even laptops”
Comment from 5 Sep 2026 in “Poetry book that Anthropic tried to censor” “It's fast and can run even on low-resource devices.”
Comment from 6 Apr 2026 in “Show HN: I Built Paul Graham's Intellectual Captcha Idea” - Comment from 16 Feb 2026 in “Rolling your own serverless OCR in 40 lines of code”
Good results on complex documents
“It has good layout recognition quality, good text recognition quality, and they actually tested it on Apple Silicon laptops.”
Comment from 13 Mar 2026 in “Can I Run AI locally?” “I've had good results with glm-ocr on complex documents”
Comment from 1 Jul 2026 in “Launch HN: Parsewise (YC P25) – Reason Across Documents with an API” Runs well in parallel across cores
“I ran 20 instances of it in parallel to utilize 20 CPU cores so the avg time came down nicely.”
Comment from 11 Feb 2026 in “GLM-OCR: Accurate × Fast × Comprehensive” “That's actually amazing, and might give me a way to use all the cores I have lying around.”
Comment from 17 Feb 2026 in “GLM-OCR: Accurate × Fast × Comprehensive”
Other OCR models people recommend
The four most recommended other OCR models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Mistral OCR | 69 | 40 | 63% | 12 | — | — |
| PaddleOCR | 19 | 4 | 83% | 8 | — | Approved |
| GLM-OCRThis page | 16 | 4 | 80% | 7 | — | Approved |
| DeepSeek-OCR | 12 | 4 | 75% | 9 | — | Approved |
| dots.ocr | 8 | 1 | 89% | 5 | — | — |
What people said
23 of the 26 comments that mention it, newest first. Each links to the original comment.
“GLM-OCR does much better than Claude, can be running on pretty miserly hardware locally, even laptops”
“Gemini 4.7 Flash will give better OCR results that Qwen or GLM w/ 10GB.”
“slightly less accurate but faster and cheaper”
“still have to live with hallucinations and the model not following the schema”
“I've had good results with glm-ocr on complex documents”
“do pretty darn well at a tiny size”
“passing something via GLM-OCR to extract all text and feed it to another model feels more practical”
“It's fast and can run even on low-resource devices.”
“this is already a small and fast model when hosted via MLX on macOS”
“Seems to work for single images but the large pdf gives me connection timeouts”
“GLM-OCR by itself is the best first thing to try locally”
“Perhaps the greatest benefit of GLM-OCR is speed: it's only a 0.9 billion parameter model”
“It has good layout recognition quality, good text recognition quality, and they actually tested it on Apple Silicon laptops.”
“GLM-OCR didn't work because it returns all text on the screen”
“That's actually amazing, and might give me a way to use all the cores I have lying around.”
“can run on CPU with good quality”
“makes it much easier to install”
“this looks really cool and, given I'm looking for OCR at the moment, I'm pretty interested”
“I ran 20 instances of it in parallel to utilize 20 CPU cores so the avg time came down nicely.”
“GLM-OCR is my favorite so far”
“extracting footnotes and similar from the full text of academic works”
“these new models are a lot better”
“This is actually the thing I really desperately need.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.