π Model Description
base_model:
- Tongyi-MAI/Z-Image-Turbo
GGUF quantized version of the Z-Image text encoder (Qwen 3 4b)
Recommended:
- Qwen34b-imatrix-IQ4XS.gguf - default pick
- Qwen34b-imatrix-Q3KM.gguf - if you really need that extra 200mb
- Qwen34b-Q80.gguf - near identical results to FP16
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
Qwen_3_4b-FP16.gguf
Recommended
LFS
FP16
|
7.5 GB | Download |
|
Qwen_3_4b-IQ4_XS.gguf
LFS
Q4
|
2.13 GB | Download |
|
Qwen_3_4b-Q3_K_M.gguf
LFS
Q3
|
1.93 GB | Download |
|
Qwen_3_4b-Q6_K.gguf
LFS
Q6
|
3.08 GB | Download |
|
Qwen_3_4b-Q8_0.gguf
LFS
Q8
|
3.99 GB | Download |
|
Qwen_3_4b-imatrix-IQ4_XS.gguf
LFS
Q4
|
2.11 GB | Download |
|
Qwen_3_4b-imatrix-Q3_K_M.gguf
LFS
Q3
|
1.93 GB | Download |