SCAIL-2 · realrebelai

SCAIL-2 Q6_K

This file is exactly 13,755,408,032 bytes — 12.81 GiB / 13.76 GB at an effective 6.712 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

12.81 GiB · 1 file

llama.cpp

llama-cli -hf realrebelai/SCAIL-2_GGUF:Q6_K

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

Hugging Face CLI

hf download realrebelai/SCAIL-2_GGUF SCAIL-2-Q6_K.gguf

Direct download

SCAIL-2-Q6_K.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.

Repository →

Size

12.81 GiB

13.76 GB

Effective bpw

6.712

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata