Qwen2.5-14B-Instruct-abliterated · mradermacher
Qwen2.5-14B-Instruct-abliterated IQ3_S
This file is exactly 6,693,020,064 bytes — 6.23 GiB / 6.69 GB at an effective 3.625 bits per weight. The nominal rate for IQ3_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
6.23 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen2.5-14B-Instruct-abliterated-GGUF:IQ3_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Qwen2.5-14B-Instruct-abliterated-GGUF Qwen2.5-14B-Instruct-abliterated.IQ3_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
6.23 GiB
6.69 GB
Effective bpw
3.625
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata