r1-1776-distill-llama-70b · unsloth
r1-1776-distill-llama-70b BF16
This file is exactly 141,117,915,520 bytes — 131.43 GiB / 141.12 GB at an effective 16.001 bits per weight. The nominal rate for BF16 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 3 file(s), summed
Get it
131.43 GiB · 3 files
llama.cpp
llama-cli -hf unsloth/r1-1776-distill-llama-70b-GGUF:BF16
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/r1-1776-distill-llama-70b-GGUF --include "BF16/r1-1776-distill-llama-70b.BF16-*-of-*.gguf"
This quantization is split across 3 files totalling 131.43 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 3 required
- BF16/r1-1776-distill-llama-70b.BF16-00001-of-00003.gguf
- BF16/r1-1776-distill-llama-70b.BF16-00002-of-00003.gguf
- BF16/r1-1776-distill-llama-70b.BF16-00003-of-00003.gguf
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
131.43 GiB
141.12 GB
Effective bpw
16.001
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata