LLM EXPLORER 57,252 MODELS INDEXED

Qwen3 VL 2B Thinking FP8 by unsloth

By unsloth · 113 downloads
HF Repo ↗ Copy URL

Qwen3 VL 2B Thinking FP8 is an open-source language model by unsloth. Features: 2b LLM, VRAM: 3.5GB, License: apache-2.0.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388 Base model:quantized:qwen/qwen... Base model:qwen/qwen3-vl-2b-th...   Conversational   Fp8   Image-text-to-text   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-FP8 

Qwen3 VL 2B Thinking FP8 Parameters and Internals

LLM NameQwen3 VL 2B Thinking FP8
Repository 🤗https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-FP8 
Base Model(s)  Qwen3 VL 2B Thinking FP8   Qwen/Qwen3-VL-2B-Thinking-FP8
Model Size2b
Required VRAM3.5 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_vl
Model Files  3.5 GB: 1-of-1
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 FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen 3 VL 2B Instruct Heretic0K / 4.3 GB442
Typhoon Ocr1.5 2B0K / 4.3 GB5502925
Qwen3 VL 2B Instruct FP80K / 3.5 GB6506343
SingGuard 2B0K / 4.3 GB7477
MAI UI 2B0K / 4.3 GB391354
UI Venus 1.5 2B0K / 4.9 GB141142
ZwZ 2B0K / 4.9 GB585
Qwen3 VL 2B Thinking FP80K / 3.5 GB61132
Qwen3 VL 2B Thinking0K / 4.3 GB74744115
Qwen3 VL 2B Thinking0K / 4.3 GB821
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-VL-2B-Thinking-FP8.