DeepSeek-R1-Distill-Qwen-32B-abliterated-v2 · mradermacher
DeepSeek-R1-Distill-Qwen-32B-abliterated-v2 I1-IQ3_S
This file is exactly 14,436,895,552 bytes — 13.45 GiB / 14.44 GB at an effective 3.525 bits per weight. The nominal rate for I1-IQ3_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
13.45 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/DeepSeek-R1-Distill-Qwen-32B-abliterated-v2-i1-GGUF:I1-IQ3_S
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-IQ3_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
13.45 GiB
14.44 GB
Effective bpw
3.525
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata