Qwen3.5-27B-Uncensored · mradermacher

Qwen3.5-27B-Uncensored I1-IQ3_XS

This file is exactly 11,967,129,312 bytes — 11.15 GiB / 11.97 GB at an effective 3.559 bits per weight. The nominal rate for I1-IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

11.15 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-27B-Uncensored-i1-GGUF:I1-IQ3_XS

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

Hugging Face CLI
hf download mradermacher/Qwen3.5-27B-Uncensored-i1-GGUF Qwen3.5-27B-Uncensored.i1-IQ3_XS.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.

Size
11.15 GiB
11.97 GB
Effective bpw
3.559
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen3.5-27B-Uncensored I1-IQ3_XS — exact size and VRAM — ossmodeldb