LLM EXPLORER 57,918 MODELS INDEXED

Nanonets OCR S by nanonets

By nanonets · 52151 downloads

Nanonets OCR S is an open-source language model by nanonets. Features: 3b LLM, VRAM: 7.5GB, Context: 125K, Instruction-Based, LLM Explorer Score: 0.32.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-3b-...   Conversational   En   Endpoints compatible   Eval-results   Image-text-to-text   Instruct   Ocr   Pdf2markdown   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow

Nanonets OCR S Parameters and Internals

LLM NameNanonets OCR S
Repository πŸ€—https://huggingface.co/nanonets/Nanonets-OCR-s 
Base Model(s)  Qwen/Qwen2.5-VL-3B-Instruct   Qwen/Qwen2.5-VL-3B-Instruct
Model Size3b
Required VRAM7.5 GB
Updated2026-08-10
Maintainernanonets
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2_5_VLForConditionalGeneration
Context Length128000
Model Max Length128000
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Nanonets OCR S

Best Alternatives
Context / RAM
Downloads
Likes
Nanonets OCR2 3B125K / 7.5 GB659329511
Qwen2.5 VL 3B Instruct125K / 7.5 GB7336490683
Typhoon Ocr 3B125K / 7.5 GB3569139
Spatial SSRL 3B125K / 8.2 GB1617
NV Reason CXR 3B125K / 8.1 GB90031
CapRL 3B125K / 7.5 GB23047
ScaleCUA 3B125K / 7.5 GB26113
CapRL Eval 3B125K / 7.5 GB878
Nanonets OCR S Bf16125K / 7.5 GB962
Qwen2.5 VL 3B Instruct125K / 7.5 GB27106
Note: green Score (e.g. "73.2") means that the model is better than nanonets/Nanonets-OCR-s.