parakeet-unified-en-0.6b · handy-computer

parakeet-unified-en-0.6b Q4_K_M

This file is exactly 477,274,496 bytes — 0.44 GiB / 0.48 GB at an effective 6.175 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), summedFrom the file· 961 tensors parsed

Get it

0.44 GiB · 1 file
llama.cpp
llama-cli -hf handy-computer/parakeet-unified-en-0.6b-gguf:Q4_K_M

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

Hugging Face CLI
hf download handy-computer/parakeet-unified-en-0.6b-gguf parakeet-unified-en-0.6b-Q4_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.

Repository →
Size
0.44 GiB
0.48 GB
Effective bpw
6.175
from real bytes ÷ params
Tensors
961
Header
0.09 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
688
Q4_K
194
F16
48
Q8_0
31

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.