What are the hardware requirements for Nanonets OCR S Bf16?

Nanonets OCR S Bf16 requires approximately 7.5 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nanonets OCR S Bf16 and how large is it?

Nanonets OCR S Bf16 is developed by mlx-community, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nanonets OCR S Bf16?

Nanonets OCR S Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nanonets OCR S Bf16 by mlx-community — VRAM 7.5GB, 125K context

Name: Nanonets OCR S Bf16
Author: mlx-community

Nanonets OCR S Bf16 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 7.5GB, Context: 125K, Instruction-Based, LLM Explorer Score: 0.18.

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

Model Card on HF 🤗: https://huggingface.co/mlx-community/Nanonets-OCR-s-bf16

Nanonets OCR S Bf16 Parameters and Internals

LLM Name	Nanonets OCR S Bf16
Repository 🤗	https://huggingface.co/mlx-community/Nanonets-OCR-s-bf16
Base Model(s)	Qwen/Qwen2.5-VL-3B-Instruct Qwen/Qwen2.5-VL-3B-Instruct
Model Size	3b
Required VRAM	7.5 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen2_5_vl
Instruction-Based	Yes
Model Files	5.4 GB: 1-of-2 2.1 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen2_5_VLForConditionalGeneration
Context Length	128000
Model Max Length	128000
Transformers Version	4.52.3
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Nanonets OCR S Bf16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Nanonets OCR S Bf16

Best Alternatives	Context / RAM	Downloads	Likes
Nanonets OCR2 3B	125K / 7.5 GB	659329	511
Qwen2.5 VL 3B Instruct	125K / 7.5 GB	7336490	683
Nanonets OCR S	125K / 7.5 GB	52151	1591
Hi Token	125K / 8.1 GB	33	1
Typhoon Ocr 3B	125K / 7.5 GB	356913	9
SpatialBlock 3B Direct	125K / 7.5 GB	62	1
SpatialBlock 3B Reason	125K / 8.1 GB	45	0
Qwen2.5 Vl 3B Idp	125K / 7.5 GB	9	1
...V L Rank8 Dr0.05 Lr1e 04 Wu0.1	125K / 7.5 GB	7	1
Spatial SSRL 3B	125K / 8.2 GB	161	7

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nanonets-OCR-s-bf16.