canary-180m-flash · handy-computer

canary-180m-flash Q8_0

This file is exactly 218,447,552 bytes — 0.20 GiB / 0.22 GB at an effective 9.242 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 789 tensors parsed

Get it

0.20 GiB · 1 file
llama.cpp
llama-cli -hf handy-computer/canary-180m-flash-gguf:Q8_0

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

Hugging Face CLI
hf download handy-computer/canary-180m-flash-gguf canary-180m-flash-Q8_0.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.

Repository →
Size
0.20 GiB
0.22 GB
Effective bpw
9.242
from real bytes ÷ params
Tensors
789
Header
0.16 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
558
Q8_0
197
F16
34

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.