mlx-community/PP-OCRv6-tiny-det-GGUF overview
PP OCRv6 tiny detector — CrispEmbed GGUF Files: PP OCRv6 tiny det f16.gguf and PP OCRv6 tiny det crispasr q4 k policy.gguf . The detector path is kept at F16 i…
Runs locally from ~0.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | mlx-community/PP-OCRv6-tiny-det-GGUF |
|---|---|
| Author | mlx-community |
| Pipeline | — |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-07-31T13:57:39.000Z |
Model README
---
library_name: crispembed
license: apache-2.0
tags: [ocr, pp-ocrv6, gguf, crispembed]
---
PP-OCRv6 tiny detector — CrispEmbed GGUF
Files: PP-OCRv6_tiny_det-f16.gguf and PP-OCRv6_tiny_det-crispasr-q4_k-policy.gguf.
The detector path is kept at F16 in the q4-policy artifact for output parity. crispembed-diff final probability-map cosine: 0.999997616.
Source: PaddlePaddle PP-OCRv6, Apache-2.0. Large files are generated and tested with CrispEmbed’s PP-OCRv6 runtime.
Run mlx-community/PP-OCRv6-tiny-det-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models