LLM EXPLORER 57,918 MODELS INDEXED

Qwen3 VL 8B Thinking Bnb 4bit by unsloth

By unsloth · 363 downloads
HF Repo ↗ Copy URL

Qwen3 VL 8B Thinking Bnb 4bit is an open-source language model by unsloth. Features: 8b LLM, VRAM: 7.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388   4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-vl-8b-th...   Bitsandbytes   Conversational   Image-text-to-text   Quantized   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-bnb-4bit 

Qwen3 VL 8B Thinking Bnb 4bit Parameters and Internals

LLM NameQwen3 VL 8B Thinking Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-bnb-4bit 
Base Model(s)  Qwen3 VL 8B Thinking   Qwen/Qwen3-VL-8B-Thinking
Model Size8b
Required VRAM7.2 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_vl
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Quantization Type4bit
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 VL 8B Thinking Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...L 8B Instruct Unsloth Bnb 4bit0K / 7.7 GB2423122
Qwen3 VL 8B Instruct Bnb 4bit0K / 7.2 GB113224
Qwen3 VL 8B Instruct 4bit0K / 5.7 GB23656
...Vl 2 8B Thinking 2603 MLX 8bit0K / 9.8 GB71
Qwen3 VL 8B Instruct 8bit0K / 9.8 GB11575
...L 8B Thinking Unsloth Bnb 4bit0K / 8.4 GB11325
Qwen3 VL 8B Thinking 8bit0K / 9.8 GB781
Qwen3 VL 8B Instruct 6bit0K / 7.8 GB442
Qwen3 VL 8B Thinking 6bit0K / 7.8 GB261
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-VL-8B-Thinking-bnb-4bit.