SeFi-Image-5B-turbo · realrebelai

SeFi-Image-5B-turbo Q6_K

This file is exactly 4,144,101,792 bytes — 3.86 GiB / 4.14 GB at an effective 6.667 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

3.86 GiB · 1 file

llama.cpp

llama-cli -hf realrebelai/SeFi-Image-5B-Turbo:Q6_K

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

Hugging Face CLI

hf download realrebelai/SeFi-Image-5B-Turbo SeFi-5B-Turbo-Q6_K.gguf

Direct download

SeFi-5B-Turbo-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

3.86 GiB

4.14 GB

Effective bpw

6.667

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata