What are the hardware requirements for Qwen2.5 VL 3B Instruct?

Qwen2.5 VL 3B Instruct 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 Qwen2.5 VL 3B Instruct and how large is it?

Qwen2.5 VL 3B Instruct is developed by Qwen, 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 Qwen2.5 VL 3B Instruct?

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

Qwen2.5 VL 3B Instruct by Qwen — VRAM 7.5GB, 125K context

Name: Qwen2.5 VL 3B Instruct
Author: Qwen

Qwen2.5 VL 3B Instruct is an open-source language model by Qwen. Features: 3b LLM, VRAM: 7.5GB, Context: 125K, Instruction-Based, LLM Explorer Score: 0.33.

Arxiv:2308.12966 Arxiv:2309.00071 Arxiv:2409.12191 Conversational Deploy:azure En Endpoints compatible Eval-results Image-text-to-text Instruct Multimodal Qwen2 5 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct

Qwen2.5 VL 3B Instruct Parameters and Internals

LLM Name	Qwen2.5 VL 3B Instruct
Repository 🤗	https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct
Model Size	3b
Required VRAM	7.5 GB
Updated	2026-08-09
Maintainer	Qwen
Model Type	qwen2_5_vl
Instruction-Based	Yes
Model Files	4.0 GB: 1-of-2 3.5 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen2_5_VLForConditionalGeneration
Context Length	128000
Model Max Length	128000
Transformers Version	4.41.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen2.5 VL 3B Instruct 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

Quantized Models of the Qwen2.5 VL 3B Instruct

Model	Likes	Downloads	VRAM
Qwen2.5 VL 3B Instruct Heretic	1	1023	7 GB
Qwen2.5 VL 3B Instruct AWQ	65	362366	3 GB
Qwen2.5 VL 3B Instruct GGUF	27	58534	0 GB
Apollo VL Edge 3B	4	7	7 GB
...L 3B Instruct GPTQ Safetensors	0	38	2 GB
Nanonets OCR2 3B 8bit	1	103	4 GB
...L 3B Instruct Unsloth Bnb 4bit	16	5323	3 GB
...wen2.5 VL 3B Instruct Bnb 4bit	5	4363	2 GB
Qwen2.5 VL 3B Instruct 4bit	5	3235	3 GB
Holo1 3B 4bit	1	27	3 GB

Best Alternatives to Qwen2.5 VL 3B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Nanonets OCR2 3B	125K / 7.5 GB	659329	511
Nanonets OCR S	125K / 7.5 GB	52151	1591
EVAN 3B	125K / 8.1 GB	78	0
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
Rex Omni	125K / 8.1 GB	14657	65
Satquery Qwen Vl 3B Merged	125K / 7.5 GB	24	1
SpatialBlock 3B Direct	125K / 7.5 GB	62	1
Hi Token	125K / 8.1 GB	33	1

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-VL-3B-Instruct.