Xiaomi-OCR-0-GGUF
Xiaomi-OCR-0 is a compact 0.8B OCR-specialized vision-language model based on Qwen3.5-0.8B-Base, designed for unified document parsing and OCR-centric understanding. It is trained on an approximately 170M-sample OCR-focused corpus using Q-Mask text anchoring, continued pretraining, and mixed-task reinforcement learning, enabling document parsing, OCR-based visual question answering, and key information extraction. The model is designed to handle standard, scanned, warped, photographed, and skewed documents, while also supporting structured outputs such as Markdown, OTSL tables, LaTeX formulas, and JSON-based information extraction. Xiaomi-OCR-0 on Hugging Face — https://hf.co/xiaomi-research/Xiaomi-OCR-0.
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|---|---|---|---|---|
| Xiaomi-OCR-0.BF16.gguf | BF16 | 1.52 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| Xiaomi-OCR-0.Q3_K_L.gguf | Q3_K_L | 491 MB | Link | Lower quality but usable, good for low RAM availability. |
| Xiaomi-OCR-0.Q3_K_M.gguf | Q3_K_M | 466 MB | Link | Low quality. |
| Xiaomi-OCR-0.Q4_K_M.gguf | Q4_K_M | 529 MB | Link | Good quality, default size for most use cases, recommended. |
| Xiaomi-OCR-0.Q4_K_S.gguf | Q4_K_S | 505 MB | Link | Slightly lower quality with more space savings, recommended. |
| Xiaomi-OCR-0.Q5_K_M.gguf | Q5_K_M | 578 MB | Link | High quality, recommended. |
| Xiaomi-OCR-0.Q5_K_S.gguf | Q5_K_S | 564 MB | Link | High quality, recommended. |
| Xiaomi-OCR-0.Q6_K.gguf | Q6_K | 630 MB | Link | Very high quality, near perfect, recommended. |
| Xiaomi-OCR-0.mmproj-bf16.gguf | mmproj-bf16 | 207 MB | Link | Multimodal projection file in BF16 format. Used for vision/language models. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp