What are the hardware requirements for RolmOCR?

RolmOCR requires approximately 16.6 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 RolmOCR and how large is it?

RolmOCR is developed by reducto, a model with 7b 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 RolmOCR?

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

RolmOCR by reducto — VRAM 16.6GB, 125K context

Name: RolmOCR
Author: reducto

RolmOCR is an open-source language model by reducto. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.29.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-... Conversational Dataset:allenai/olmocr-mix-022... Endpoints compatible Image-text-to-text Instruct Qwen2 5 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/reducto/RolmOCR

RolmOCR Parameters and Internals

LLM Name	RolmOCR
Repository 🤗	https://huggingface.co/reducto/RolmOCR
Base Model(s)	Qwen/Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct
Model Size	7b
Required VRAM	16.6 GB
Updated	2026-08-09
Maintainer	reducto
Model Type	qwen2_5_vl
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.7 GB: 4-of-4
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	4.50.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the RolmOCR 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 RolmOCR

Best Alternatives	Context / RAM	Downloads	Likes
OmniLong Qwen2.5 VL 7B	512K / 16.6 GB	7	2
Qwen2.5 VL 7B Instruct	125K / 16.7 GB	8740905	1666
OlmOCR 2 7B 1025 FP8	125K / 10 GB	540426	253
PosterCopilot	125K / 16.7 GB	29	1
Qwen2.5 VL 7B Instruct FP4	125K / 7.2 GB	49165	3
X Reasoner 7B	125K / 16.5 GB	1030	10
Qwen2.5 VL 7B Instruct NVFP4	125K / 7.2 GB	8092	16
ZwZ 7B	125K / 16.6 GB	32	10
Qwen2.5 VL 7B Instruct FP8	125K / 10 GB	1009	8
OlmOCR 2 7B 1025 Bf16	125K / 16.6 GB	154	2

Note: green Score (e.g. "73.2") means that the model is better than reducto/RolmOCR.