Qwen3.5-122B-A10B-abliterix BF16

This file is exactly 244,314,011,328 bytes — 227.54 GiB / 244.31 GB at an effective 16.006 bits per weight. The nominal rate for BF16 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 6 file(s), summed

Get it

227.54 GiB · 6 files
llama.cpp
llama-cli -hf random257/Qwen3.5-122B-A10B-Wangzhang-Abliterix-No-MTP:BF16

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

Hugging Face CLI
hf download random257/Qwen3.5-122B-A10B-Wangzhang-Abliterix-No-MTP --include "Qwen3.5-122B-A10B-Wangzhang-Abliterix-No-MTP-BF16-*-of-*.gguf"

This quantization is split across 6 files totalling 227.54 GiB. You need every part — the first is not a smaller version of the model.

Size
227.54 GiB
244.31 GB
Effective bpw
16.006
from real bytes ÷ params
Tensors
Header
GGUF metadata