Tiers and Runtimes
Tiers express parsing quality and cost. Small-model backends and VLM engines are configured independently; they are not tier names.
| Tier | Purpose | Local execution |
|---|---|---|
flash |
Fast previews, indexing, native documents | Native PDF text / document parsing; Flash OCR for scans and images |
basic |
OCR, formulas, and tables | ONNX or Torch small models; no local VLM required |
standard |
Complex layouts and high-quality parsing | Small models + VLM |
advanced |
More demanding quality requirements | Standard models and runtime, with more inference computation |
PDF and images support all four tiers. Office, OpenDocument, RTF, EPUB, OFD, HTML, and CSV/TSV use local Flash and whole-document parsing. Pass tier="flash" explicitly for these formats in the local Python SDK. Plain text is not parsed, but can be indexed and read by the document library.
Default selection
mineru-kit parseand local Pythonparse()default to Standard for PDFs.- After discovering service capabilities, the document library prefers Standard, then Basic for PDF/images. If neither is available, it returns
quality_tier_unavailablerather than silently choosing Flash or uploading to the official service. - Advanced is explicit. Prepare models and managed service capacity as Standard; there is no separate Advanced model download.
- Library
readconsumes cached results without starting a new parse. Without an explicit tier, it prefers cached Advanced, Standard, then Basic results.
Backends and engines
| Environment | Automatic small models | Automatic VLM |
|---|---|---|
| Apple Silicon / MPS | Torch / MPS | llama.cpp |
| Linux / Windows, base package | ONNX / CPU when no Torch accelerator runtime is available | llama.cpp |
Linux, accelerator and full |
Torch | vLLM, otherwise installed LMDeploy |
Windows, accelerator and full |
Torch | LMDeploy |
| CPU environment | ONNX / CPU | llama.cpp |
Automatic selection uses installed dependencies and available devices. An explicit choice with missing dependencies fails instead of silently selecting another backend. ONNX small models run on CPU; VLM device selection is independent.
Intel XPU is excluded from automatic LMDeploy selection. Linux prefers an installed XPU-compatible vLLM and otherwise falls back to llama.cpp; Windows uses llama.cpp.
model:
small_backend: auto
vlm:
engine: auto
small_backend accepts auto/onnx/torch; engine accepts auto/llama-cpp/vllm/lmdeploy. macOS defaults to llama.cpp.
Resources and platform boundaries
Native text parsing needs no inference models. Basic can run on CPU. Standard / Advanced speed and memory depend on the VLM engine, input size, and concurrency. Plan for at least 16 GB of system memory for higher-throughput local deployment. NVIDIA deployments also need an engine-supported GPU, driver, and sufficient free VRAM; 8 GB is only a planning starting point, not a guarantee for every workload.
For Apple Silicon, at least 16 GB of unified memory and a direct macOS installation are recommended. Existing AMD and vendor adaptations remain on MinerU <4; this page does not extend their compatibility claims to 4.0.
See extension modules for installation and Model Source for downloads and configuration.