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.
QW
qwen2-0_5b-instruct
Qwen · Qwen
Params494M
Context32K
Q4_K_M0.4 GB
QW
Qwen1.5-0.5B-Chat-AWQ-fp16
Qwen · Qwen
Params620M
Context32K
Q4_K_M0.4 GB
QW
qwen2.5-32b-instruct
Qwen · Qwen
Params32.8B
Context128K
Q4_K_M19.9 GB
QW
Qwen3Vl 8b Thinking
Qwen · Qwen
Params8.19B
Context256K
Q4_K_M5.0 GB
QW
qwen2-7b-instruct
Qwen · Qwen
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
qwen2.5-72b-instruct
Qwen · Qwen
Params73B
Context32K
Q4_K_M44.0 GB
QW
Qwen3 235B A22B
Qwen · Qwen
Params235B
Context40K
Q4_K_M142.2 GB
QW
Qwen3Vl 4b Thinking
Qwen · Qwen
Params4B
Context256K
Q4_K_M2.5 GB
QW
Qwen3Vl 30b A3B Thinking
Qwen · Qwen
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen3Vl 235b A22B Instruct
Qwen · Qwen
Params235B
Context256K
Q4_K_M142.2 GB
QW
Qwen3 Next 80B A3B Thinking
Qwen · Qwen
Params80B
Context256K
Q4_K_M48.4 GB
QW
Qwen3Vl 32b Thinking
Qwen · Qwen
Params32.8B
Context256K
Q4_K_M19.8 GB
QW
Qwen1.5-7B-Chat-AWQ-fp16
Qwen · Qwen
Params7.72B
Context32K
Q4_K_M4.8 GB
QW
Qwen3Vl 2b Thinking
Qwen · Qwen
Params1.72B
Context256K
Q4_K_M1.1 GB
QW
Qwen1.5-1.8B-Chat-AWQ-fp16
Qwen · Qwen
Params1.84B
Context32K
Q4_K_M1.2 GB
QW
Qwen2 72B Instruct
Qwen · Qwen
Params72.7B
Context32K
Q4_K_M47.4 GB
QW
CodeQwen1.5 7B Chat
Qwen · Qwen
Params7.25B
Context64K
Q4_K_M4.7 GB
QW
Qwen2 57B A14B Instruct
Qwen · Qwen
Params57.4B
Context32K
Q4_K_M34.9 GB
QW
Qwen3Vl 235b A22B Thinking
Qwen · Qwen
Params235B
Context256K
Q4_K_M142.2 GB
QW
Qwen1.5-14B-Chat-AWQ-fp16
Qwen · Qwen
Params14.2B
Context32K
Q4_K_M9.2 GB
QW
Qwen1.5-4B-Chat-AWQ-fp16
Qwen · Qwen
Params3.95B
Context32K
Q4_K_M2.5 GB
QW
Qwen1.5 32B Chat
Qwen · Qwen
Params32.5B
Context32K
Q4_K_M19.7 GB
QW
Qwen1.5-72B-Chat-AWQ-fp16
Qwen · Qwen
Params72.3B
Context32K
Smallest28.5 GB
QW
Qwen1.5-110B-Chat-AWQ-fp16
Qwen · Qwen
Params111B
Context32K
Smallest41.2 GB