The story so far
Weights, every dated article, and repo commits on one rail.
15 repo commits since the weights landed
Teal is the weights (2024-11-22), grey ticks are repo commits.
GOT-OCR-2.0-hf
stepfun-ai Apache 2.0 out 23 months ago
561M parameters, images and text in, text out.
Verified 2026-10-25 Rank #766 in LLMs · score 71.2 method v1 Sources 3 Downloads 30d 22.9k · #446 of 619 tracked
Do people use it?22.9kdownloads, 30 days#446 of 619 we track · below the median243 likesHugging Face2026-10-24
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 15 Spaces.
- As a service0no API provider listed
- On own hardware0quantized builds
- Built on31 fine-tunes · 2 adapters · 0 merges
- In apps15Hugging Face Spaces
Top Spaces running it: yonigozlan/GOT-OCR-Transformers ♥ 83 · Ansemin101/Markit_v2 ♥ 2 · Um34ER/bazaar-bridge-ocr ♥ 2 · Sensei13k/OCR ♥ 1
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 0.3 GB at INT4, 0.7 GB at FP8, 1.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
3 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
3 derivatives on the Hub, most of them adapters
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
What the card says
1 cited sentence
Use-case evidence
4 use cases
What it is good at 4 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
- Understand images and videostructuraldecision-model estimate p=0.98tag: image-text-to-textpipeline: image-text-to-text+1 more
- Extract text from documentsstructuraldecision-model estimate p=1.00name: OCR
- Work across languagesstructuraldecision-model estimate p=0.82tag: multilingual
- Run on a laptop or phonestructuraldecision-model estimate p=0.91fits: edge
Facts
19 fields
Listed in LLMs
Facts
- GOT-OCR-2.0-hf has 561M parameters. (safetensors metadata, observed 2026-10-24)
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2024-11-22, last modified 2025-01-31. (HF API, observed 2026-10-24)
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Architectures | GotOcr2ForConditionalGeneration |
| Model type | got_ocr2 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 560,528,640 |
| Size band | S |
| MoE | no |
| Languages | multilingual |
| Papers | arXiv:2409.01704, arXiv:2405.14295, arXiv:2312.06109 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for GOT-OCR-2.0-hf: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 1.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.7 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.3 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
All variants
3 variants
Lineage
finetune: 1adapter: 2
Top variants (3 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| huggingface-mic/got_ocr2-mic | finetune | — | 13.0M | S | — | huggingface-mic | 0 | 258 |
| CharanS247/got-ocr2-telugu-handwritten | adapter | — | — | — | apache-2.0 | CharanS247 | 0 | 127 |
| nicogptai/bhcerhbvhfrbhvtrhbbtvr | adapter | — | — | — | apache-2.0 | nicogptai | 0 | 0 |
Repository changelog
15 commits
Repository changelog 15 commits
| Date | Commit | SHA |
|---|---|---|
| 2025-01-31 | Update preprocessor_config.json | d3017ef |
| 2025-01-30 | Update README.md | f445e41 |
| 2025-01-30 | Update README.md | 4a5190b |
| 2025-01-30 | Upload GotOcr2ForConditionalGeneration | 813b588 |
| 2025-01-27 | Upload GotOcr2ForConditionalGeneration | 1e806a7 |
| 2025-01-24 | Upload GotOcr2ForConditionalGeneration | 6be64fb |
| 2025-01-24 | Upload GotOcr2ForConditionalGeneration | b6e5417 |
| 2025-01-21 | Upload GotOcr2ForConditionalGeneration | c3255ae |
| 2025-01-06 | Upload GotOcr2ForConditionalGeneration | da2e9d4 |
| 2024-11-29 | Upload GotOcr2ForConditionalGeneration | b42a53f |
| 2024-11-25 | Upload GotOcr2ForConditionalGeneration | 74b7f49 |
| 2024-11-22 | Upload processor | 5015eba |
| 2024-11-22 | Upload tokenizer | d4780c5 |
| 2024-11-22 | Upload GotOcr2ForConditionalGeneration | d6273bc |
| 2024-11-22 | initial commit | f57d36f |
Papers
3 papers
Papers 3
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Similar models
3 models
Similar models
- surya-ocr-2 · 686M same size band (S), same task (image-text-to-text), more providers
- GOT-OCR2_0 · 716M same size band (S), same task (image-text-to-text), permissive license
- LFM2.5-VL-450M · 449M same size band (S), same task (image-text-to-text)
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:43 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:15 UTC · Last verified 2026-10-25
Follow GOT-OCR-2.0-hf
Watch this model
- /feeds/models/stepfun-ai--GOT-OCR-2.0-hf.xml(RSS 2.0) · every change to GOT-OCR-2.0-hf
- /feeds/families/stepfun-ai--GOT-OCR-2.0.xml(RSS 2.0) · every change across the GOT-OCR-2.0 family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.