Qwen-Image · unsloth

Qwen-Image Q4_K_M

This file is exactly 13,127,088,672 bytes — 12.23 GiB / 13.13 GB at an effective 5.140 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 1933 tensors parsed

Get it

12.23 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/Qwen-Image-GGUF:Q4_K_M

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download unsloth/Qwen-Image-GGUF qwen-image-Q4_K_M.gguf
Direct download

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.

Repository →
Size
12.23 GiB
13.13 GB
Effective bpw
5.140
from real bytes ÷ params
Tensors
1933
Header
0.15 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
1087
Q4_K
560
Q6_K
232
Q5_K
48
BF16
6

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.