Qwen3

unsloth 's Collections

gpt-oss

Unsloth Dynamic 2.0 Quants

Qwen3

DeepSeek R1 (All Versions)

Gemma 3n

Gemma 3

Llama 4

Phi-4 (All Versions)

Qwen3-Coder

Unsloth 4-bit Dynamic Quants

Deepseek V3 (All Versions)

Text-to-Speech (TTS) models

Diffusion + FLUX 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

Llama 3.2 Vision

Qwen 2.5 Coder

Llama 3.1 Collection

Qwen 2.5

Load 4bit models 4x faster

4bit Instruct Models

updated 1 day ago

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants.

Upvote

189

unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF

31B • Updated 14 days ago • 223k • 197

Note Qwen3-25-07 (July 2025) Updated models:
unsloth/Qwen3-4B-Instruct-2507-GGUF

0.0B • Updated 8 days ago • 41.9k • 34
unsloth/Qwen3-4B-Thinking-2507-GGUF

0.0B • Updated 8 days ago • 34.5k • 34
unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF

235B • Updated 20 days ago • 59.8k • 64
unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF

Text Generation • 480B • Updated 14 days ago • 104k • 147
unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF

Text Generation • 235B • Updated 16 days ago • 89.5k • 90
unsloth/Qwen3-30B-A3B-GGUF

Text Generation • 31B • Updated Jun 8 • 184k • 240
unsloth/Qwen3-32B-GGUF

Text Generation • 33B • Updated Jun 8 • 43.1k • 84
unsloth/Qwen3-235B-A22B-GGUF

Text Generation • 235B • Updated Jun 8 • 20.8k • 68
unsloth/Qwen3-14B-GGUF

Text Generation • 15B • Updated Jun 8 • 26.4k • 65
unsloth/Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 8 • 25.1k • 65
unsloth/Qwen3-4B-GGUF

Text Generation • 4B • Updated Jun 8 • 46.4k • 68
unsloth/Qwen3-1.7B-GGUF

Text Generation • 2B • Updated Jun 8 • 26.3k • 36
unsloth/Qwen3-0.6B-GGUF

Text Generation • 0.6B • Updated Jun 23 • 32.1k • 71
unsloth/Qwen3-30B-A3B-128K-GGUF

Text Generation • 31B • Updated May 25 • 9.85k • 55

Note 128K Context Length GGUFs:
unsloth/Qwen3-235B-A22B-128K-GGUF

Text Generation • 235B • Updated May 25 • 4.19k • 34
unsloth/Qwen3-32B-128K-GGUF

Text Generation • 33B • Updated May 25 • 4.76k • 24
unsloth/Qwen3-14B-128K-GGUF

Text Generation • 15B • Updated May 25 • 4.29k • 19
unsloth/Qwen3-8B-128K-GGUF

Text Generation • 8B • Updated May 25 • 3.29k • 16
unsloth/Qwen3-4B-128K-GGUF

Text Generation • 4B • Updated May 25 • 2.8k • 22
unsloth/Qwen3-32B-unsloth-bnb-4bit

Text Generation • 24B • Updated May 14 • 8.96k • 12

Note Dynamic 4-bit safetensors to fine-tune/deploy:
unsloth/Qwen3-14B-unsloth-bnb-4bit

Text Generation • 9B • Updated May 13 • 73.5k • 8
unsloth/Qwen3-8B-unsloth-bnb-4bit

5B • Updated May 13 • 68.8k • 8
unsloth/Qwen3-4B-unsloth-bnb-4bit

Text Generation • 3B • Updated May 13 • 68.1k • 9
unsloth/Qwen3-1.7B-unsloth-bnb-4bit

Text Generation • 1B • Updated May 13 • 45.4k • 6
unsloth/Qwen3-0.6B-unsloth-bnb-4bit

Text Generation • 0.4B • Updated Jun 23 • 38.6k • 16
unsloth/Qwen3-30B-A3B-Instruct-2507

Text Generation • 31B • Updated 16 days ago • 3.35k • 9

Note Original 16-bit (Instruct):
unsloth/Qwen3-4B-Instruct-2507

Text Generation • 4B • Updated 8 days ago • 5.28k • 4
unsloth/Qwen3-4B-Thinking-2507

Text Generation • 4B • Updated 8 days ago • 887 • 2
unsloth/Qwen3-32B

33B • Updated May 13 • 14.1k • 10
unsloth/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated 17 days ago • 386 • 7
unsloth/Qwen3-30B-A3B

31B • Updated May 13 • 4.33k • 16
unsloth/Qwen3-14B

15B • Updated May 13 • 21.3k • 10
unsloth/Qwen3-8B

Text Generation • 8B • Updated May 13 • 30.7k • • 9
unsloth/Qwen3-4B

4B • Updated May 13 • 32k • 12
unsloth/Qwen3-1.7B

2B • Updated May 13 • 23.8k • 4
unsloth/Qwen3-0.6B

0.6B • Updated Jun 23 • 25.4k • 12
unsloth/Qwen3-32B-bnb-4bit

18B • Updated May 14 • 12.3k • 6

Note BitsandBytes 4-bit safetensors:
unsloth/Qwen3-30B-A3B-bnb-4bit

Updated May 13 • 24.3k • 16
unsloth/Qwen3-14B-bnb-4bit

8B • Updated May 13 • 4.75k • 2
unsloth/Qwen3-8B-bnb-4bit

5B • Updated May 13 • 6.55k • 2
unsloth/Qwen3-4B-bnb-4bit

2B • Updated May 13 • 3.82k • 1
unsloth/Qwen3-0.6B-bnb-4bit

0.4B • Updated Jun 23 • 11.3k • 2
unsloth/Qwen3-1.7B-bnb-4bit

1B • Updated May 13 • 5.44k • 2
unsloth/Qwen3-14B-Base-unsloth-bnb-4bit

Text Generation • 15B • Updated about 1 month ago • 4.53k • 3
unsloth/Qwen3-8B-Base-unsloth-bnb-4bit

Text Generation • 5B • Updated about 1 month ago • 8.34k • 2

Note (Base) - Our Dynamic 4-bit safetensors to fine-tune/deploy:
unsloth/Qwen3-4B-Base-unsloth-bnb-4bit

Text Generation • 2B • Updated May 13 • 14.1k • 1
unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit

Text Generation • 1B • Updated May 13 • 3.12k • 1
unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit

Text Generation • 0.4B • Updated about 1 month ago • 6.04k • 2
unsloth/Qwen3-30B-A3B-Base

Text Generation • 31B • Updated May 13 • 1.83k • 3

Note (Base) Original 16-bit:
unsloth/Qwen3-14B-Base

Text Generation • 15B • Updated about 1 month ago • 2.54k • • 1
unsloth/Qwen3-8B-Base

Text Generation • 8B • Updated about 1 month ago • 4.81k • • 2
unsloth/Qwen3-1.7B-Base

Text Generation • 2B • Updated May 13 • 3.46k • 3
unsloth/Qwen3-4B-Base

Text Generation • 4B • Updated May 13 • 39.6k • 2
unsloth/Qwen3-0.6B-Base

Text Generation • 0.6B • Updated about 1 month ago • 8.7k • 4
unsloth/Qwen3-30B-A3B-Base-bnb-4bit

Updated May 13 • 1.43k

Note (Base) BitsandBytes 4-bit safetensors:
unsloth/Qwen3-14B-Base-bnb-4bit

Text Generation • 15B • Updated about 1 month ago • 1.33k
unsloth/Qwen3-8B-Base-bnb-4bit

Text Generation • 5B • Updated about 1 month ago • 1.87k • 1
unsloth/Qwen3-4B-Base-bnb-4bit

Text Generation • 2B • Updated May 13 • 1.4k
unsloth/Qwen3-1.7B-Base-bnb-4bit

Text Generation • 1B • Updated May 13 • 4.08k
unsloth/Qwen3-0.6B-Base-bnb-4bit

Text Generation • 0.4B • Updated about 1 month ago • 4.54k
unsloth/Qwen3-32B-FP8

Text Generation • 33B • Updated May 11 • 1.09k • 1

Note FP8 versions:
unsloth/Qwen3-30B-A3B-Instruct-2507-FP8

Text Generation • 31B • Updated 16 days ago • 549 • 5
unsloth/Qwen3-14B-FP8

Text Generation • 15B • Updated May 11 • 2.29k • 1
unsloth/Qwen3-8B-FP8

Text Generation • 8B • Updated May 11 • 1.22k
unsloth/Qwen3-4B-FP8

Text Generation • 4B • Updated May 11 • 878
unsloth/Qwen3-1.7B-FP8

Text Generation • 2B • Updated May 11 • 75
unsloth/Qwen3-0.6B-FP8

Text Generation • 0.6B • Updated May 11 • 39
unsloth/Qwen3-235B-A22B-Instruct-2507-FP8

Text Generation • 235B • Updated 24 days ago • 753 • 3
unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF

31B • Updated 14 days ago • 70.8k • 74

Upvote

189

Collection guide
Browse collections