Qwen3.5-35B-A3B-HighIQ-Prototype-II · mradermacher
Qwen3.5-35B-A3B-HighIQ-Prototype-II I1-IQ2_S
This file is exactly 10,652,480,576 bytes — 9.92 GiB / 10.65 GB at an effective 2.459 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
9.92 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-35B-A3B-HighIQ-Prototype-II-i1-GGUF:I1-IQ2_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Qwen3.5-35B-A3B-HighIQ-Prototype-II-i1-GGUF Qwen3.5-35B-A3B-HighIQ-Prototype-II.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
9.92 GiB
10.65 GB
Effective bpw
2.459
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata