LLM EXPLORER 62,076 MODELS INDEXED

Qwen3 VL 2B Thinking by Qwen

By Qwen · 74744 downloads

Qwen3 VL 2B Thinking is an open-source language model by Qwen. Features: 2b LLM, VRAM: 4.3GB, License: apache-2.0, LLM Explorer Score: 0.29.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388   Conversational   Deploy:azure   Endpoints compatible   Image-text-to-text   Qwen3 vl   Region:us   Safetensors

Qwen3 VL 2B Thinking Parameters and Internals

LLM NameQwen3 VL 2B Thinking
Repository πŸ€—https://huggingface.co/Qwen/Qwen3-VL-2B-Thinking 
Model Size2b
Required VRAM4.3 GB
Updated2026-08-10
MaintainerQwen
Model Typeqwen3_vl
Model Files  4.3 GB
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the Qwen3 VL 2B Thinking

Model
Likes
Downloads
VRAM
...L 2B Thinking Unsloth Bnb 4bit11772 GB

Best Alternatives to Qwen3 VL 2B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 2B Instruct0K / 4.3 GB2204577448
Qwen3 VL Reranker 2B0K / 4.3 GB764323212
WeVisDoc 2B0K / 4.9 GB59914
PhysBrain1.5 2B0K / 4.3 GB24913
Qwen3 VL 2B Instruct FP80K / 3.5 GB6506343
Typhoon Ocr1.5 2B0K / 4.3 GB5502925
Foresight Qwen3vl 2B Sft0K / 4.3 GB541
...hlighter Qwen3 Vl 2B Rl Merged0K / 3.3 GB221
SingGuard 2B0K / 4.3 GB7477
ImageShield MMCF 2B Vl0K / 4.3 GB331
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-VL-2B-Thinking.