cstr/nanonets-ocr-s-crispembed-GGUF

Nanonets-OCR-s CrispEmbed GGUF

Nanonets-OCR-s (small) vision-language model converted to GGUF for OCR with CrispEmbed.

Models

File	Quant	Size
nanonets-ocr-s-f16.gguf	F16	~3.6 GB
nanonets-ocr-s-q8_0.gguf	Q8_0	~1.9 GB
nanonets-ocr-s-q4_k.gguf	Q4_K	~1.0 GB

Architecture

• Base: Nanonets-OCR-s (Qwen2-VL pruned fine-tune, Apache-2.0)
• Params: ~1.5B (16 layers vs 28 in Qwen2-VL-2B)
• Languages: 12+ including English, German, French, Spanish, Chinese, Japanese, Arabic
• Task: Document OCR, multilingual text recognition

Usage

Runs on the existing qwen2vl_ocr engine in CrispEmbed (no custom engine needed):

from crispembed import CrispOcrPipeline

ocr = CrispOcrPipeline(vlm_model="nanonets-ocr-s-q8_0.gguf")
text = ocr.recognize("document.png")

Original Model

nanonets/Nanonets-OCR-s — Qwen2-VL pruned fine-tune (16L vs 28L), 12+ languages including German.

License

Apache-2.0

Provenance and EU AI Act Art. 53 note

• Upstream model: nanonets/Nanonets-OCR-s — published by nanonets.
• Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.