DeepSeek-R1-Distill-Qwen-32B-abliterated-v2 I1-IQ1_M

This file is exactly 7,932,160,832 bytes — 7.39 GiB / 7.93 GB at an effective 1.937 bits per weight. The nominal rate for I1-IQ1_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

7.39 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/DeepSeek-R1-Distill-Qwen-32B-abliterated-v2-i1-GGUF:I1-IQ1_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-i1-GGUF DeepSeek-R1-Distill-Qwen-32B-abliterated-v2.i1-IQ1_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
7.39 GiB
7.93 GB
Effective bpw
1.937
from real bytes ÷ params
Tensors
Header
GGUF metadata
DeepSeek-R1-Distill-Qwen-32B-abliterated-v2 I1-IQ1_M — exact size and VRAM — ossmodeldb