AuraFlow-v0.3 · city96

AuraFlow-v0.3 Q3_K_M

This file is exactly 3,126,551,840 bytes — 2.91 GiB / 3.13 GB at an effective 3.647 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.91 GiB · 1 file
llama.cpp
llama-cli -hf city96/AuraFlow-v0.3-gguf:Q3_K_M

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

Hugging Face CLI
hf download city96/AuraFlow-v0.3-gguf aura_flow_0.3-Q3_K_M.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
2.91 GiB
3.13 GB
Effective bpw
3.647
from real bytes ÷ params
Tensors
Header
GGUF metadata
AuraFlow-v0.3 Q3_K_M — exact size and VRAM — ossmodeldb