What are the hardware requirements for SearchQwen2.5 3B?

SearchQwen2.5 3B requires approximately 6.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SearchQwen2.5 3B and how large is it?

SearchQwen2.5 3B is developed by alibaba-pai, 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 SearchQwen2.5 3B?

SearchQwen2.5 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SearchQwen2.5 3B by alibaba-pai — VRAM 6.8GB, 32K context

Name: SearchQwen2.5 3B
Author: alibaba-pai

SearchQwen2.5 3B is an open-source language model by alibaba-pai. Features: 3b LLM, VRAM: 6.8GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.27.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Conversational Deep-search En Endpoints compatible Function-calling Instruct Qwen Qwen2 Region:us Safetensors Search-agent Sharded Tensorflow Tool-use

Model Card on HF 🤗: https://huggingface.co/alibaba-pai/SearchQwen2.5-3B

SearchQwen2.5 3B Parameters and Internals

LLM Name	SearchQwen2.5 3B
Repository 🤗	https://huggingface.co/alibaba-pai/SearchQwen2.5-3B
Base Model(s)	Qwen/Qwen2.5-3B-Instruct Qwen/Qwen2.5-3B-Instruct
Model Size	3b
Required VRAM	6.8 GB
Updated	2026-08-26
Maintainer	alibaba-pai
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.8 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.56.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the SearchQwen2.5 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 SearchQwen2.5 3B

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B	128K / 6.2 GB	52745	806
VibeThinker 3B	128K / 6.2 GB	361	0
Saba2 3B	128K / 6.2 GB	6	0
Tessa T1 3B	117K / 6.2 GB	10	5
UIGEN T1.5 3B	117K / 6.2 GB	7	1
Qwen2.5 3B Instruct	32K / 6.2 GB	5889234	545
...in Anomaly Qwen2.5 3B Instruct	32K / 6.2 GB	196	1
... Instruct Sheldon RLVR Math V1	32K / 6.2 GB	876	0
Zen Ingress 1 3B Sft Merged	32K / 6.2 GB	834	1
SmallThinker 3B Preview	32K / 6.8 GB	30529	412

Note: green Score (e.g. "73.2") means that the model is better than alibaba-pai/SearchQwen2.5-3B.