XI

Xiaomi OCR 0

XiaomiGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters773M
Context256K
Layers25
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Xiaomi OCR 0 needs about 1.5 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 0.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Xiaomi OCR 0 – a 0.8B vision‑language model for document parsing and OCR

Xiaomi OCR 0 is a 0.8B model built on Qwen3.5-0.8B-Base. It supports document parsing, OCR‑centric VQA, and key information extraction. The model is available in several GGUF quantizations for local inference with llama.cpp and Ollama.

Good at

  • Document parsing
  • OCR‑centric question answering
  • Key information extraction

Limits

  • No vision support in the base model
  • Requires a GPU with at least 8 GB VRAM for full context
  • License is apache‑2.0

Best for

  • Parsing scanned reports
  • Extracting tables from invoices
  • Converting handwritten notes to text

Who it’s for. Developers building OCR pipelines that need a single, lightweight model. Researchers testing vision‑language capabilities on local hardware. Enterprises requiring an open‑source solution for document understanding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.6 GB
Fits Get file →
Q8_00.8 GB 1.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.54 GB file, ~1.5 GB memory). If 16 GB VRAM is available, Q6_K (0.65 GB file, ~1.6 GB memory) offers higher precision. The Q8_0 quant (0.83 GB file, ~1.8 GB memory) provides the best quality for larger budgets.

What GPU do you need for Xiaomi OCR 0?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (0.8 GB file, about 1.8 GB in use).

Which Xiaomi OCR 0 quant should you choose?

Q4_K_M is the usual starting point for Xiaomi OCR 0: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters773M
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized byrichardyoung
FamilyXiaomi
Licenseapache-2.0
Downloads (HF)806
Last updated2026-10-20

Frequently asked questions about Xiaomi OCR 0

How much VRAM does Xiaomi OCR 0 need?

About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Xiaomi OCR 0 on an 8 GB GPU?

Yes, with Q8_0: the 0.8 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Xiaomi OCR 0 GGUF?

It depends on the quant: file is 0.0 GB, Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB.

What context length does Xiaomi OCR 0 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download Xiaomi OCR 0 GGUF?

The files are on Hugging Face in the richardyoung/Xiaomi-OCR-0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Xiaomi OCR 0 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Xiaomi OCR 0 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 1.5 GB of VRAM at 8 k context, which fits in 8 GB.

Does the model support vision tasks?

Yes, it includes a vision projector for document parsing and OCR tasks.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Xiaomi-OCR-0

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More Xiaomi models

All Xiaomi →

Other tiny models

All tiny models →