SeFi-Image-5B-turbo · realrebelai

SeFi-Image-5B-turbo Q4_K_M

This file is exactly 3,155,086,752 bytes — 2.94 GiB / 3.16 GB at an effective 5.076 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.94 GiB · 1 file

llama.cpp

llama-cli -hf realrebelai/SeFi-Image-5B-Turbo:Q4_K_M

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

Hugging Face CLI

hf download realrebelai/SeFi-Image-5B-Turbo SeFi-5B-Turbo-Q4_K_M.gguf

Direct download

SeFi-5B-Turbo-Q4_K_M.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

2.94 GiB

3.16 GB

Effective bpw

5.076

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata