qwen27b-abliterated-Fable-MTP · hotdogs
qwen27b-abliterated-Fable-MTP IQ4_NL
This file is exactly 15,998,539,680 bytes — 14.90 GiB / 16.00 GB at an effective 4.685 bits per weight. The nominal rate for IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
14.90 GiB · 1 file
llama.cpp
llama-cli -hf hotdogs/qwen27B-Agent-R2-abliterated-preview:IQ4_NL
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download hotdogs/qwen27B-Agent-R2-abliterated-preview GGUF/qwen27B-Agent-R2-abliterated-preview-MTP.IQ4_NL.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
14.90 GiB
16.00 GB
Effective bpw
4.685
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata