What are the hardware requirements for ICM R2?

ICM R2 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 ICM R2 and how large is it?

ICM R2 is developed by SeerRay-Lab, 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 ICM R2?

ICM R2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

ICM R2 by SeerRay-Lab — VRAM 16.6GB, 125K context

Name: ICM R2
Author: SeerRay-Lab

ICM R2 is an open-source language model by SeerRay-Lab. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.3.

Arxiv:2601.18197 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-... Best-of-n Conversational Critic-model Dataset:seerray-lab/gaia-datas... En Endpoints compatible Gui Gui-agent Image-text-to-text Instruct Qwen2.5-vl Qwen2 5 vl Region:us Safetensors Sharded Tensorflow Test-time-scaling Vision Vision-language-model

Model Card on HF 🤗: https://huggingface.co/SeerRay-Lab/ICM-r2

ICM R2 Parameters and Internals

LLM Name	ICM R2
Repository 🤗	https://huggingface.co/SeerRay-Lab/ICM-r2
Base Model(s)	Qwen/Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct
Model Size	7b
Required VRAM	16.6 GB
Updated	2026-09-17
Maintainer	SeerRay-Lab
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
Supported Languages	en
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the ICM R2 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 ICM R2

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
OlmOCR 2 7B 1025	125K / 16.6 GB	244728	157
RolmOCR	125K / 16.6 GB	224280	589
SpatialBlock 7B Direct	125K / 16.6 GB	49	0
Qwen2.5 VL 7B Instruct FP4	125K / 7.2 GB	49165	3
SpaSEViLA Cold Start 7B	125K / 16.6 GB	27	0
Cosmos Reason1 7B	125K / 16.6 GB	62913	244
OlmOCR 7B 0825 FP8	125K / 10 GB	38011	10

Note: green Score (e.g. "73.2") means that the model is better than SeerRay-Lab/ICM-r2.