Qwen2.5-14B-Instruct-abliterated · mradermacher

Qwen2.5-14B-Instruct-abliterated I1-IQ3_M

This file is exactly 6,916,539,040 bytes — 6.44 GiB / 6.92 GB at an effective 3.746 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

6.44 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Qwen2.5-14B-Instruct-abliterated-i1-GGUF:I1-IQ3_M

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

Hugging Face CLI

hf download mradermacher/Qwen2.5-14B-Instruct-abliterated-i1-GGUF Qwen2.5-14B-Instruct-abliterated.i1-IQ3_M.gguf

Direct download

Qwen2.5-14B-Instruct-abliterated.i1-IQ3_M.gguf

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

6.44 GiB

6.92 GB

Effective bpw

3.746

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata