What are the hardware requirements for Egx Qwen2.5 Vl 3B?

Egx Qwen2.5 Vl 3B requires approximately 7.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Egx Qwen2.5 Vl 3B and how large is it?

Egx Qwen2.5 Vl 3B is developed by Keretos1, 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 Egx Qwen2.5 Vl 3B?

Egx Qwen2.5 Vl 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Egx Qwen2.5 Vl 3B by Keretos1 — VRAM 7.6GB

Name: Egx Qwen2.5 Vl 3B
Author: Keretos1

Egx Qwen2.5 Vl 3B is an open-source language model by Keretos1. Features: 3b LLM, VRAM: 7.6GB, LLM Explorer Score: 0.25.

Qwen2 5 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Keretos1/egx-qwen2.5-vl-3b

Egx Qwen2.5 Vl 3B Parameters and Internals

LLM Name	Egx Qwen2.5 Vl 3B
Repository 🤗	https://huggingface.co/Keretos1/egx-qwen2.5-vl-3b
Model Size	3b
Required VRAM	7.6 GB
Updated	2026-09-06
Maintainer	Keretos1
Model Type	qwen2_5_vl
Model Files	2.0 GB: 1-of-4 2.0 GB: 2-of-4 2.0 GB: 3-of-4 1.6 GB: 4-of-4
Model Architecture	Qwen2_5_VLForConditionalGeneration
Model Max Length	131072
Transformers Version	5.8.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Egx Qwen2.5 Vl 3B 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 Egx Qwen2.5 Vl 3B

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
Typhoon Ocr 3B	125K / 7.5 GB	356913	9
Qwen2.5 Vl 3B Mllmu Ft	125K / 7.5 GB	110	0
Papo Step150	125K / 8.1 GB	32	1
Satquery Qwen Vl 3B Merged	125K / 7.5 GB	24	1
SpatialBlock 3B Direct	125K / 7.5 GB	62	1
Rex Omni	125K / 8.1 GB	14657	65
Hi Token	125K / 8.1 GB	33	1

Note: green Score (e.g. "73.2") means that the model is better than Keretos1/egx-qwen2.5-vl-3b.