No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from openbmb/MiniCPM-OCR-1.0-gguf
All models by openbmb →This repository hosts the GGUF build of MiniCPM-OCR 1.0 for llama.cpp. For the original weights, the full model card, and benchmarks, see the base repository.
MiniCPM-OCR 1.0 (1.3B) parses documents into text, tables, formulas, charts, and seals, and supports key information extraction, for Chinese and English documents and PDFs.
Every tier needs the vision projector as well — --model takes the LLM GGUF, --mmproj takes
the projector:
The projector is 4× only; there is no 16× variant for this model.
Prefer Q8_0 for code- or XML-heavy pages.
--n-gpu-layers 999 offloads everything to GPU; use 0 for CPU-only.
Thinking is already disabled inside the embedded chat template — no extra flag is needed, and
enable_thinking cannot turn it back on. (If you convert the weights yourself instead of using
these files, start the server with --chat-template-kwargs '{"enable_thinking": false}'.)
llama-server handles one request at a time by default, so keep queue_mode=serial and
max_workers=1.
Single RTX 5090 (32 GB), F16 weights: model + projector load ≈2.3 s; one table crop
(1,312 prompt / 265 output tokens) ≈1.0 s; VRAM ≈26 GB at --ctx-size 40960.
CPU-only (48 threads): one table image end-to-end (layout + recognition + assembly) ≈21 s.
Build llama.cpp and further options: llama.cpp deployment guide.
Speculative decoding works in llama.cpp with the
DSpark draft GGUF via --spec-type draft-dspark.
Installation, model downloads, GPU memory, input formats, and unexpected outputs: FAQ.
Model weights, code, and documentation are released under the Apache License 2.0.
llama-server \ --model ./MiniCPM-OCR-1_0-Q8_0.gguf \ --mmproj ./mmproj-model-f16-4x.gguf \ --host 0.0.0.0 --port 18499 \ --ctx-size 40960 \ --n-gpu-layers 999llama-mtmd-cli \ -m ./MiniCPM-OCR-1_0-Q8_0.gguf \ --mmproj ./mmproj-model-f16-4x.gguf \ --image page.png -p "Text Recognition:" \ --jinja -ngl 99 -c 8192 --temp 0minicpmvocr parse --config sdk/minicpmvocr/configs/minicpmvocr.yaml \ --backend llamacpp --server-url http://127.0.0.1:18499 \ --model minicpm-ocr \ --set layout.device=cuda:0 \ --set pipeline.queue_mode=serial \ --set pipeline.max_workers=1 \ --input doc.pdf --output doc.md