GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

sabafallah/Unlimited-OCR-GGUF overview

Unlimited OCR GGUF for llama.cpp GGUF model files for running baidu/Unlimited OCR in llama.cpp's MTMD multimodal support. Unlimited OCR is DeepSeek OCR v1's De…

ggufbase_model:baidu/Unlimited-OCRbase_model:quantized:baidu/Unlimited-OCRendpoints_compatibleregion:usconversational

Runs locally from ~439.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
4,768
Likes
1
Pipeline

Repository Files & Downloads

5 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
mmproj-unlimited-ocr-bf16.ggufGGUFBF16788.1 MBDownload
mmproj-unlimited-ocr-q8_0.ggufGGUFQ8_0439.9 MBDownload
unlimited-ocr-Q4_K_M.ggufGGUFQ4_K_M1.82 GBDownload
unlimited-ocr-bf16.ggufGGUFBF165.47 GBDownload
unlimited-ocr-q8_0.ggufGGUFQ8_02.91 GBDownload

Model Details

Model IDsabafallah/Unlimited-OCR-GGUF
Authorsabafallah
Pipeline
License
Base modelbaidu/Unlimited-OCR
Last modified2026-07-13T07:33:39.000Z

Model README

---

base_model:

  • baidu/Unlimited-OCR

---

Unlimited-OCR GGUF (for llama.cpp)

GGUF model files for running baidu/Unlimited-OCR in llama.cpp's MTMD (multimodal) support.

Unlimited-OCR is DeepSeek-OCR v1's DeepEncoder + a DeepSeek-V2 MoE decoder, with the decoder

attention replaced by R-SWA (Reference Sliding Window Attention). llama.cpp support lands in

two stacked PRs (the same GGUF files work for both):

  • PR1 - converter, decoder runs full MHA: #24969
  • PR2 - R-SWA in the decoder (stacked on PR1): #24975

These models are only compatible with the PR branches, not upstream llama.cpp master.

A third PR is independent of the stack and targets master directly:

The mmproj files were re-uploaded on 2026-07-13 and now carry preproc_max_tiles = 32, matching

the reference implementation. Unlimited-OCR shares DeepSeek-OCR v1's projector type, so without

#25614 llama.cpp ignores the key and falls back to v1's cap of 9 - tall or dense pages are then

split into a coarser tile grid than the reference. Older mmproj files keep working either way.

---

Download

huggingface-cli download sabafallah/Unlimited-OCR-GGUF --include "unlimited-ocr-bf16.gguf" --local-dir gguf_models/baidu
huggingface-cli download sabafallah/Unlimited-OCR-GGUF --include "mmproj-unlimited-ocr-bf16.gguf" --local-dir gguf_models/baidu

---

Run example

llama-mtmd-cli:

build/bin/llama-mtmd-cli \
  -m gguf_models/baidu/unlimited-ocr-bf16.gguf \
  --mmproj gguf_models/baidu/mmproj-unlimited-ocr-bf16.gguf \
  --image tools/mtmd/test-1.jpeg -p "document parsing." \
  --chat-template deepseek-ocr --no-jinja \
  --temp 0 --flash-attn off --no-warmup \
  -n 4096 -c 16384 \
  --dry-multiplier 0.8 --dry-base 1.75 --dry-allowed-length 35 \
  --dry-penalty-last-n 128 --dry-sequence-breaker none

The DRY flags are a weak loop guard mirroring the reference implementation's

no_repeat_ngram_size=35 / ngram_window=128. Keep the allowed length high:

aggressive DRY settings garble the model's HTML table output.

Files

| file | |

|---|---|

| unlimited-ocr-bf16.gguf | LM bf16 |

| unlimited-ocr-q8_0.gguf | LM q8_0 |

| unlimited-ocr-Q4_K_M.gguf | LM Q4_K_M |

| mmproj-unlimited-ocr-bf16.gguf | mmproj bf16 |

| mmproj-unlimited-ocr-q8_0.gguf | mmproj q8_0 |

Run sabafallah/Unlimited-OCR-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models