LLM EXPLORER 66,845 MODELS INDEXED

Qwen3 VL 2B Thinking by unsloth

By unsloth · 82 downloads
HF Repo ↗ Copy URL

Qwen3 VL 2B Thinking is an open-source language model by unsloth. Features: 2b LLM, VRAM: 4.3GB, License: apache-2.0, LLM Explorer Score: 0.2.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-2b-th...   Conversational   Endpoints compatible   Image-text-to-text   Qwen3 vl   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking 

Qwen3 VL 2B Thinking Parameters and Internals

LLM NameQwen3 VL 2B Thinking
Repository 🤗https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking 
Base Model(s)  Qwen3 VL 2B Thinking   Qwen/Qwen3-VL-2B-Thinking
Model Size2b
Required VRAM4.3 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_vl
Model Files  4.3 GB
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Errorsreplace

Best Alternatives to Qwen3 VL 2B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
WeVisOne VL 2B0K / 4.9 GB204939
Qwen3 VL 2B Instruct0K / 4.3 GB2204577448
Qwen3 VL Reranker 2B0K / 4.3 GB764323212
WeVisDoc 2B0K / 4.9 GB59914
Qwen3 VL 2B Thinking0K / 4.3 GB74744115
...wen3 Vl 2B Foveated Search Fp80K / 2.9 GB461
Qwen3vl 2B Ag Merged0K / 4.3 GB310
PhysBrain1.5 2B0K / 4.3 GB27213
Qwen3 VL 2B Instruct FP80K / 3.5 GB6506343
VIG Qwen3 VL Thinking 2B0K / 4.9 GB551
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-VL-2B-Thinking.