GGUF models by Qwen

54 GGUF models quantized by Qwen on Hugging Face. Sizes run from 494M to 235B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3Vl 8b Instruct
Qwen · Qwen
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
QW
Qwen3 8B Awq Compatible Instruct
Qwen · Qwen
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
QW
qwen2.5-7b-instruct
Qwen · Qwen
Params7.6B
Context128K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 4B Instruct Awq
Qwen · Qwen
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
QW
Qwen3Vl 4b Instruct
Qwen · Qwen
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
qwen2.5-1.5b-instruct
Qwen · Qwen
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
QW
qwen2.5-0.5b-instruct
Qwen · Qwen
Params630M
Context32K
Q4_K_M0.5 GB
GGUF
QW
Qwen3 14B Awq Compatible Instruct
Qwen · Qwen
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct GGUF
Qwen · Qwen
Params15B
Context128K
Q4_K_M9.4 GB
Coding
QW
qwen2.5-3b-instruct
Qwen · Qwen
Params3.4B
Context32K
Q4_K_M2.1 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct GGUF
Qwen · Qwen
Params1.78B
Context32K
Q4_K_M1.1 GB
Coding
QW
Qwen3 0.6B Instruct
Qwen · Qwen
Params596M
Context40K
Smallest0.6 GB
GGUF
QW
Qwen2.5 Coder 14B Instruct AWQ
Qwen · Qwen
Params29B
Context128K
Q4_K_M18.0 GB
Coding
QW
Qwen3Vl 2b Instruct
Qwen · Qwen
Params1.72B
Context256K
Q4_K_M1.1 GB
Vision
QW
Qwen3 1.7B Instruct
Qwen · Qwen
Params1.72B
Context40K
Smallest1.8 GB
GGUF
QW
Qwen3 Embedding 0.6b
Qwen · Qwen
Params596M
Context32K
Smallest0.6 GB
Embedding
QW
Qwen3 32B Awq Compatible Instruct
Qwen · Qwen
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
QW
Qwen3 30B A3B
Qwen · Qwen
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct AWQ
Qwen · Qwen
Params3.4B
Context32K
Q4_K_M2.1 GB
Coding
QW
Qwen3Vl 30b A3B Instruct
Qwen · Qwen
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
QW
Qwen3Vl 32b Instruct
Qwen · Qwen
Params32.8B
Context256K
Q4_K_M19.8 GB
Vision
QW
Qwen3 Embedding 4B
Qwen · Qwen
Params4B
Context40K
Q4_K_M2.5 GB
Embedding
QW
Qwen3 Coder Next 0129
Qwen · Qwen
Params80B
Context256K
Q4_K_M48.4 GB
Coding
QW
Qwen3 Embedding 8B
Qwen · Qwen
Params7.57B
Context40K
Q4_K_M4.7 GB
Embedding
QW
Qwen2.5 Coder 32B Instruct AWQ
Qwen · Qwen
Params32.8B
Context128K
Q4_K_M39.7 GB
Coding
QW
qwen2.5-14b-instruct
Qwen · Qwen
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
QW
Qwen2.5 Coder 0.5B Instruct AWQ
Qwen · Qwen
Params630M
Context32K
Q4_K_M0.5 GB
Coding
QW
QwQ 32B
Qwen · Qwen
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
QW
Qwen3 Next 80B A3B Instruct
Qwen · Qwen
Params80B
Context256K
Q4_K_M48.4 GB
GGUF
QW
qwen2-1_5b-instruct
Qwen · Qwen
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF

About Qwen on Hugging Face

Qwen has published 54 GGUF models that ggufmodels.com tracks, across families such as Qwen. The most downloaded are Qwen3Vl 8b Instruct, Qwen3 8B Awq Compatible Instruct and qwen2.5-7b-instruct.

The quants Qwen publishes most often are Q8_0 (52), Q4_K_M (49), Q6_K (37) and Q5_K_M (37). Their Q4_K_M files range from 0.4 to 142.2 GB. Parameter counts run from 494M to 235B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has Qwen published?

54 models are listed here, mainly from the Qwen families. The most downloaded is Qwen3Vl 8b Instruct.

Which quants does Qwen publish?

The most common are Q8_0 (52 models), Q4_K_M (49 models), Q6_K (37 models) and Q5_K_M (37 models).

Keep browsing