canary-1b · handy-computer

canary-1b F16

This file is exactly 2,047,537,728 bytes — 1.91 GiB / 2.05 GB at an effective 16.036 bits per weight. The nominal rate for F16 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

1.91 GiB · 1 file

llama.cpp

llama-cli -hf handy-computer/canary-1b-gguf:F16

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

Hugging Face CLI

hf download handy-computer/canary-1b-gguf canary-1b-F16.gguf

Direct download

canary-1b-F16.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

1.91 GiB

2.05 GB

Effective bpw

16.036

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata