parakeet-tdt-0.6b-v2 · handy-computer
parakeet-tdt-0.6b-v2 Q6_K
This file is exactly 600,408,576 bytes — 0.56 GiB / 0.60 GB at an effective 7.774 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summedFrom the file· 697 tensors parsed
Get it
0.56 GiB · 1 file
llama.cpp
llama-cli -hf handy-computer/parakeet-tdt-0.6b-v2-gguf:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download handy-computer/parakeet-tdt-0.6b-v2-gguf parakeet-tdt-0.6b-v2-Q6_K.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
0.56 GiB
0.60 GB
Effective bpw
7.774
from real bytes ÷ params
Tensors
697
Header
0.07 MB
GGUF metadata
What this quantization actually contains
per-tensor types, parsed from the GGUF header
F32
424
Q6_K
218
F16
48
Q8_0
7
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.