Nanonets OCR S is an open-source language model by unsloth. Features: 3.8b LLM, VRAM: 7.5GB, Context: 125K, LLM Explorer Score: 0.19.
| LLM Name | Nanonets OCR S |
| Repository 🤗 | https://huggingface.co/unsloth/Nanonets-OCR-s |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.5 GB |
| Updated | 2026-08-10 |
| Maintainer | unsloth |
| Model Type | qwen2_5_vl |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2_5_VLForConditionalGeneration |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |