DeepSeek-V2-Lite-Instruct-Abliterated-15-1.2 IQ4_XS

This file is exactly 8,647,691,904 bytes — 8.05 GiB / 8.65 GB at an effective 4.405 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

8.05 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/DeepSeek-V2-Lite-Instruct-Abliterated-15-1.2-GGUF:IQ4_XS

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

Hugging Face CLI
hf download mradermacher/DeepSeek-V2-Lite-Instruct-Abliterated-15-1.2-GGUF DeepSeek-V2-Lite-Instruct-Abliterated-15-1.2.IQ4_XS.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
8.05 GiB
8.65 GB
Effective bpw
4.405
from real bytes ÷ params
Tensors
Header
GGUF metadata
DeepSeek-V2-Lite-Instruct-Abliterated-15-1.2 IQ4_XS — exact size and VRAM — ossmodeldb