| base_model: mikoy92/Unlimited-OCR-bf16-mlx | |
| license: mit | |
| language: | |
| - multilingual | |
| pipeline_tag: image-text-to-text | |
| tags: | |
| - mlx | |
| - mlx-vlm | |
| - ocr | |
| - vision-language | |
| - baidu | |
| - deepseekocr | |
| - quantized | |
| - 4-bit | |
| - affine | |
| library_name: mlx | |
| # Unlimited-OCR 4-bit MLX | |
| This is a 4-bit affine MLX quantization of [`mikoy92/Unlimited-OCR-bf16-mlx`](https://huggingface.co/mikoy92/Unlimited-OCR-bf16-mlx), converted with `mlx-vlm`. | |
| Quantization settings: | |
| - mode: `affine` | |
| - bits: `4` | |
| - group size: `64` | |
| - observed effective bits per weight during conversion: `5.883` | |
| Because this is a vision-language OCR model, `mlx-vlm` does not aggressively quantize every multimodal tensor; the effective bits-per-weight can be higher than exactly 4-bit. | |
| ## Usage | |
| ```bash | |
| pip install -U mlx-vlm | |
| mlx_vlm.generate \ | |
| --model mikoy92/Unlimited-OCR-4bit-mlx \ | |
| --image /path/to/image.png \ | |
| --prompt "Extract all readable text from this image." \ | |
| --max-tokens 512 \ | |
| --temperature 0 | |
| ``` | |
| ## Validation | |
| Before upload, this checkpoint was loaded locally with `mlx_vlm.generate` and produced OCR text/table output on a document-image smoke test. | |