Total04-DeepSeek-R1-Distill-Llama-70B-heretic I1-Q2_K_S

This file is exactly 24,471,946,272 bytes — 22.79 GiB / 24.47 GB at an effective 2.775 bits per weight. The nominal rate for I1-Q2_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

22.79 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Total04-DeepSeek-R1-Distill-Llama-70B-heretic-i1-GGUF:I1-Q2_K_S

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

Hugging Face CLI
hf download mradermacher/Total04-DeepSeek-R1-Distill-Llama-70B-heretic-i1-GGUF Total04-DeepSeek-R1-Distill-Llama-70B-heretic.i1-Q2_K_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
22.79 GiB
24.47 GB
Effective bpw
2.775
from real bytes ÷ params
Tensors
Header
GGUF metadata
Total04-DeepSeek-R1-Distill-Llama-70B-heretic I1-Q2_K_S — exact size and VRAM — ossmodeldb