LLM EXPLORER 57,918 MODELS INDEXED

Qwen3 VL 30B A3B Thinking FP8 by unsloth

By unsloth · 40 downloads
HF Repo ↗ Copy URL

Qwen3 VL 30B A3B Thinking FP8 is an open-source language model by unsloth. Features: 30b LLM, VRAM: 32.2GB, License: apache-2.0, LLM Explorer Score: 0.21.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388 Base model:quantized:qwen/qwen... Base model:qwen/qwen3-vl-30b-a...   Conversational   Fp8   Image-text-to-text   Qwen3 vl moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking-FP8 

Qwen3 VL 30B A3B Thinking FP8 Parameters and Internals

LLM NameQwen3 VL 30B A3B Thinking FP8
Repository 🤗https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking-FP8 
Base Model(s)  Qwen3 VL 30B A3B Thinking FP8   Qwen/Qwen3-VL-30B-A3B-Thinking-FP8
Model Size30b
Required VRAM32.2 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_vl_moe
Model Files  10.6 GB: 1-of-4   10.6 GB: 2-of-4   10.7 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureQwen3VLMoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Errorsreplace

Best Alternatives to Qwen3 VL 30B A3B Thinking FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 30B A3B Instruct0K / 62.3 GB488106591
Qwen3 VL 30B A3B Instruct FP80K / 32.2 GB734631115
Qwen3 VL 30B A3B Thinking0K / 62.3 GB67001200
Qwen3 VL 30B A3B Thinking FP80K / 32.2 GB4300458
Bu 30B A3b Preview0K / 62.3 GB1035263
UI Venus 1.5 30B A3B0K / 62.3 GB110735
P1 VL 30B A3B0K / 62.3 GB273
Qwen3 VL 30B A3B Instruct FP80K / 32.2 GB3491
Qwen3 VL 30B A3B Instruct0K / 62.3 GB5153
Gelato 30B A3B0K / 62.1 GB3034
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-VL-30B-A3B-Thinking-FP8.