canary-1b-v2 · cstr

canary-1b-v2 Q8_0

This file is exactly 666,894,464 bytes — 0.62 GiB / 0.67 GB at an effective 5.444 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· 712 tensors parsed

Get it

0.62 GiB · 1 file
llama.cpp
llama-cli -hf cstr/canary-ctc-aligner-GGUF:Q8_0

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

Hugging Face CLI
hf download cstr/canary-ctc-aligner-GGUF canary-ctc-aligner-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
0.62 GiB
0.67 GB
Effective bpw
5.444
from real bytes ÷ params
Tensors
712
Header
0.29 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
417
Q8_0
266
F16
29

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.