Qwen2.5-7B-Instruct-abliterated I1-Q3_K_S

This file is exactly 3,492,369,664 bytes — 3.25 GiB / 3.49 GB at an effective 3.669 bits per weight. The nominal rate for I1-Q3_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

3.25 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen2.5-7B-Instruct-abliterated-i1-GGUF:I1-Q3_K_S

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

Hugging Face CLI
hf download mradermacher/Qwen2.5-7B-Instruct-abliterated-i1-GGUF Qwen2.5-7B-Instruct-abliterated.i1-Q3_K_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
3.25 GiB
3.49 GB
Effective bpw
3.669
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen2.5-7B-Instruct-abliterated I1-Q3_K_S — exact size and VRAM — ossmodeldb