Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking I1-IQ4_XS

This file is exactly 5,070,612,640 bytes — 4.72 GiB / 5.07 GB at an effective 4.530 bits per weight. The nominal rate for I1-IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

4.72 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking-i1-GGUF:I1-IQ4_XS

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

Hugging Face CLI
hf download mradermacher/Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking-i1-GGUF Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking.i1-IQ4_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
4.72 GiB
5.07 GB
Effective bpw
4.530
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking I1-IQ4_XS — exact size and VRAM — ossmodeldb