Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking · mradermacher
Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking I1-IQ2_S
This file is exactly 3,207,768,224 bytes — 2.99 GiB / 3.21 GB at an effective 2.866 bits per weight. The nominal rate for I1-IQ2_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
2.99 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking-i1-GGUF:I1-IQ2_S
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-IQ2_S.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
2.99 GiB
3.21 GB
Effective bpw
2.866
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata