cohere-transcribe-03-2026 · handy-computer

cohere-transcribe-03-2026 Q6_K

This file is exactly 1,972,524,544 bytes — 1.84 GiB / 1.97 GB at an effective 7.639 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· 2103 tensors parsed

Get it

1.84 GiB · 1 file
llama.cpp
llama-cli -hf handy-computer/cohere-transcribe-03-2026-gguf:Q6_K

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

Hugging Face CLI
hf download handy-computer/cohere-transcribe-03-2026-gguf cohere-transcribe-03-2026-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.

Repository →
Size
1.84 GiB
1.97 GB
Effective bpw
7.639
from real bytes ÷ params
Tensors
2103
Header
0.51 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
1492
Q6_K
515
F16
96

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.