Qwen3.5-122B-A10B-heretic-v2 I1-IQ4_XS

This file is exactly 65,244,882,624 bytes — 60.76 GiB / 65.24 GB at an effective 4.274 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

60.76 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-122B-A10B-heretic-v2-i1-GGUF:I1-IQ4_XS

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-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
60.76 GiB
65.24 GB
Effective bpw
4.274
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen3.5-122B-A10B-heretic-v2 I1-IQ4_XS — exact size and VRAM — ossmodeldb