Qwen-Image-Edit-2509 · calcuis
Qwen-Image-Edit-2509 IQ4_NL
This file is exactly 39,006,331,808 bytes — 36.33 GiB / 39.01 GB at an effective 15.274 bits per weight. The nominal rate for IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.
From the file· 4 file(s), summed
Get it
36.33 GiB · 4 files
llama.cpp
llama-cli -hf calcuis/qwen-image-edit-plus-gguf:IQ4_NL
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download calcuis/qwen-image-edit-plus-gguf --include "qwen-image-edit-lite-iq4_nl.gguf"
This quantization is split across 4 files totalling 36.33 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 4 required
- qwen-image-edit-lite-iq4_nl.gguf
- qwen-image-edit-lite-v2.0-iq4_nl.gguf
- qwen-image-edit-plus-iq4_nl.gguf
- qwen-image-edit-plus-v2-iq4_nl.gguf
Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.
Size
36.33 GiB
39.01 GB
Effective bpw
15.274
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata