Qwen3.5-122B-A10B-heretic-v2 · mradermacher

Qwen3.5-122B-A10B-heretic-v2 I1-IQ3_M

This file is exactly 53,788,853,952 bytes — 50.09 GiB / 53.79 GB at an effective 3.524 bits per weight. The nominal rate for I1-IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

50.09 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-122B-A10B-heretic-v2-i1-GGUF:I1-IQ3_M

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

Hugging Face CLI
hf download mradermacher/Qwen3.5-122B-A10B-heretic-v2-i1-GGUF Qwen3.5-122B-A10B-heretic-v2.i1-IQ3_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
50.09 GiB
53.79 GB
Effective bpw
3.524
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata