Total04-DeepSeek-R1-Distill-Llama-70B-heretic I1-IQ3_XS
This file is exactly 29,307,733,024 bytes — 27.29 GiB / 29.31 GB at an effective 3.323 bits per weight. The nominal rate for I1-IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
27.29 GiB · 1 file
llama.cpp
llama-cli -hf fairy322/Total04-DeepSeek-R1-Distill-Llama-70B-heretic-i1-GGUF:I1-IQ3_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download fairy322/Total04-DeepSeek-R1-Distill-Llama-70B-heretic-i1-GGUF Total04-DeepSeek-R1-Distill-Llama-70B-heretic.i1-IQ3_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
27.29 GiB
29.31 GB
Effective bpw
3.323
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata