Qwen3-VL

unsloth 's Collections

Unsloth Dynamic 2.0 Quants

NVFP4

Gemma 4

Qwen3.6

Gemma 4 QAT

Unsloth Diffusion GGUFs

DeepSeek R1 (All Versions)

Unsloth 4-bit Dynamic Quants

Deepseek V3 (All Versions)

Text-to-Speech (TTS) models

Mistral Small 3 (All Versions)

Llama 3.2

Llama 3.3 (All Versions)

Qwen2.5-VL (All Versions)

Qwen QwQ-32B Collection

Vision/multimodal Models

Load 4bit models 4x faster

4bit Instruct Models

updated 7 days ago

Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats.

Upvote

unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF

Image-Text-to-Text • 31B • Updated Jan 1 • 74.4k • 105

Note Unsloth Dynamic GGUFs to run:
unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF

Image-Text-to-Text • 31B • Updated Jan 1 • 3.67k • 41
unsloth/Qwen3-VL-4B-Instruct-GGUF

Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 193k • 60
unsloth/Qwen3-VL-4B-Thinking-GGUF

Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 3.64k • 25
unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF

235B • Updated Dec 31, 2025 • 3.49k • 40
unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF

235B • Updated Dec 31, 2025 • 6.48k • 22
unsloth/Qwen3-VL-32B-Instruct-GGUF

Image-Text-to-Text • 33B • Updated Jan 1 • 9.71k • 28
unsloth/Qwen3-VL-32B-Thinking-GGUF

Image-Text-to-Text • 33B • Updated Jan 1 • 2.18k • 24
unsloth/Qwen3-VL-8B-Instruct-GGUF

Image-Text-to-Text • 8B • Updated Oct 31, 2025 • 31.1k • 57
unsloth/Qwen3-VL-8B-Thinking-GGUF

Image-Text-to-Text • 8B • Updated Oct 31, 2025 • 7.52k • 24
unsloth/Qwen3-VL-2B-Instruct-GGUF

Image-Text-to-Text • 2B • Updated Oct 31, 2025 • 336k • 38
unsloth/Qwen3-VL-2B-Thinking-GGUF

Image-Text-to-Text • 2B • Updated Nov 2, 2025 • 5.91k • 10
unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit

Image-Text-to-Text • 9B • Updated Oct 31, 2025 • 25.2k • 22

Note Unsloth Dynamic 4-bit Bitsandbytes to fine-tune/deploy with:
unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit

Image-Text-to-Text • 9B • Updated Oct 14, 2025 • 1.11k • 5
unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit

Image-Text-to-Text • 5B • Updated Oct 14, 2025 • 245k • 12
unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit

Image-Text-to-Text • 5B • Updated Oct 14, 2025 • 49k • 2
unsloth/Qwen3-VL-32B-Instruct-unsloth-bnb-4bit

Image-Text-to-Text • 33B • Updated Oct 21, 2025 • 1.56k • 2
unsloth/Qwen3-VL-32B-Thinking-unsloth-bnb-4bit

Image-Text-to-Text • 33B • Updated Oct 21, 2025 • 94 • 2
unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit

Image-Text-to-Text • 2B • Updated Oct 30, 2025 • 200k • 8
unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit

Image-Text-to-Text • 2B • Updated Oct 30, 2025 • 381 • 1
unsloth/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 31, 2025 • 3.99k • 9

Note 16-bit original safetensor to fine-tune/deploy with:
unsloth/Qwen3-VL-8B-Thinking

Image-Text-to-Text • 9B • Updated Oct 31, 2025 • 251 • 2
unsloth/Qwen3-VL-4B-Instruct

Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 22k • • 10
unsloth/Qwen3-VL-4B-Thinking

Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 70 • 2
unsloth/Qwen3-VL-32B-Instruct

Image-Text-to-Text • 33B • Updated Jan 1 • 252 • 5
unsloth/Qwen3-VL-235B-A22B-Instruct

236B • Updated Jan 1 • 17 • 2
unsloth/Qwen3-VL-32B-Thinking

Image-Text-to-Text • 33B • Updated Jan 1 • 127 • 3
unsloth/Qwen3-VL-235B-A22B-Thinking

236B • Updated Jan 1 • 9 • 8
unsloth/Qwen3-VL-30B-A3B-Instruct

Image-Text-to-Text • 31B • Updated Jan 1 • 353 • 2
unsloth/Qwen3-VL-30B-A3B-Thinking

Image-Text-to-Text • 31B • Updated Jan 1 • 30 • 5
unsloth/Qwen3-VL-2B-Instruct

Image-Text-to-Text • 2B • Updated Oct 31, 2025 • 3.49k • 8
unsloth/Qwen3-VL-2B-Thinking

Image-Text-to-Text • 2B • Updated Oct 31, 2025 • 89 • 1
unsloth/Qwen3-VL-8B-Instruct-bnb-4bit

Image-Text-to-Text • 9B • Updated Oct 14, 2025 • 13.1k • 4

Note 4-bit Bitsandbytes to fine-tune/deploy with:
unsloth/Qwen3-VL-4B-Thinking-bnb-4bit

Image-Text-to-Text • 5B • Updated Oct 14, 2025 • 61 • 1
unsloth/Qwen3-VL-32B-Instruct-bnb-4bit

Image-Text-to-Text • 33B • Updated Oct 21, 2025 • 544k • 5
unsloth/Qwen3-VL-8B-Thinking-bnb-4bit

Image-Text-to-Text • 9B • Updated Oct 14, 2025 • 426 • 3
unsloth/Qwen3-VL-2B-Instruct-bnb-4bit

Image-Text-to-Text • 2B • Updated Oct 30, 2025 • 984 • 3
unsloth/Qwen3-VL-4B-Instruct-bnb-4bit

Image-Text-to-Text • 5B • Updated Oct 14, 2025 • 1.76k • 2
unsloth/Qwen3-VL-2B-Thinking-bnb-4bit

Image-Text-to-Text • 2B • Updated Oct 30, 2025 • 83
unsloth/Qwen3-VL-32B-Thinking-bnb-4bit

Image-Text-to-Text • 33B • Updated Oct 21, 2025 • 52 • 2
unsloth/Qwen3-VL-8B-Instruct-FP8

Image-Text-to-Text • 9B • Updated Nov 24, 2025 • 1.2k • 7

Note FP8 to run inference/deploy:
unsloth/Qwen3-VL-4B-Instruct-FP8

Image-Text-to-Text • 5B • Updated Nov 24, 2025 • 174 • 2
unsloth/Qwen3-VL-8B-Thinking-FP8

Image-Text-to-Text • 9B • Updated Nov 24, 2025 • 114 • 2
unsloth/Qwen3-VL-4B-Thinking-FP8

Image-Text-to-Text • 5B • Updated Nov 24, 2025 • 83 • 1
unsloth/Qwen3-VL-2B-Thinking-1M-GGUF

Image-Text-to-Text • 2B • Updated Nov 1, 2025 • 2.07k • 3
unsloth/Qwen3-VL-235B-A22B-Instruct-1M-GGUF

235B • Updated Nov 1, 2025 • 953 • 2
unsloth/Qwen3-VL-235B-A22B-Thinking-1M-GGUF

235B • Updated Nov 1, 2025 • 952 • 1
unsloth/Qwen3-VL-8B-Thinking-1M-GGUF

Image-Text-to-Text • 8B • Updated Nov 1, 2025 • 1.1k • 17
unsloth/Qwen3-VL-8B-Instruct-1M-GGUF

Image-Text-to-Text • 8B • Updated Nov 1, 2025 • 796 • 7
unsloth/Qwen3-VL-30B-A3B-Instruct-1M-GGUF

Image-Text-to-Text • 31B • Updated Nov 2, 2025 • 1.57k • 6
unsloth/Qwen3-VL-30B-A3B-Thinking-1M-GGUF

Image-Text-to-Text • 31B • Updated Nov 2, 2025 • 1.11k • 6
unsloth/Qwen3-VL-32B-Instruct-1M-GGUF

Image-Text-to-Text • 33B • Updated Nov 1, 2025 • 500 • 4
unsloth/Qwen3-VL-32B-Thinking-1M-GGUF

Image-Text-to-Text • 33B • Updated Nov 2, 2025 • 1.2k • 7
unsloth/Qwen3-VL-4B-Instruct-1M-GGUF

Image-Text-to-Text • 4B • Updated Nov 1, 2025 • 931 • 5
unsloth/Qwen3-VL-4B-Thinking-1M-GGUF

Image-Text-to-Text • 4B • Updated Nov 1, 2025 • 1.28k • 3
unsloth/Qwen3-VL-2B-Instruct-1M-GGUF

Image-Text-to-Text • 2B • Updated Nov 1, 2025 • 1.47k • 6

Upvote

Collection guide
Browse collections