DeepSeek-R1-Distill-Qwen-32B-abliterated-v2 Q5_K_M

This file is exactly 23,262,157,312 bytes — 21.66 GiB / 23.26 GB at an effective 5.680 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

21.66 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/DeepSeek-R1-Distill-Qwen-32B-abliterated-v2-GGUF:Q5_K_M

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

Hugging Face CLI
hf download mradermacher/DeepSeek-R1-Distill-Qwen-32B-abliterated-v2-GGUF DeepSeek-R1-Distill-Qwen-32B-abliterated-v2.Q5_K_M.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
21.66 GiB
23.26 GB
Effective bpw
5.680
from real bytes ÷ params
Tensors
Header
GGUF metadata