Unlimited OCR is an open-source language model by baidu. Features: 3.3b LLM, VRAM: 6.7GB, Context: 32K, License: mit, LLM Explorer Score: 0.55.
| LLM Name | Unlimited OCR |
| Repository π€ | https://huggingface.co/baidu/Unlimited-OCR |
| Model Size | 3.3b |
| Required VRAM | 6.7 GB |
| Updated | 2026-08-08 |
| Maintainer | baidu |
| Model Type | unlimited-ocr |
| Model Files | |
| Model Architecture | UnlimitedOCRForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <ο½βpadβο½> |
| Vocabulary Size | 129280 |
| Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Unlimited OCR AWQ | 1 | 304197 | 2 GB |
| Unlimited OCR 8bit | 1 | 332 | 3 GB |
| Unlimited OCR 4bit | 1 | 201 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ited OCR Community FP8 Dynamic | 32K / 4.1 GB | 4265 | 1 |
| Unlimited OCR Bf16 | 32K / 6.6 GB | 295 | 1 |
| Unlimited OCR Community NVFP4 | 32K / 2.9 GB | 11 | 1 |