Chroma · silveroxides

Chroma Q6_K

This file is exactly 8,208,158,880 bytes — 7.64 GiB / 8.21 GB at an effective 7.378 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· 643 tensors parsed

Get it

7.64 GiB · 1 file
llama.cpp
llama-cli -hf silveroxides/Chroma-GGUF:Q6_K

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

Hugging Face CLI
hf download silveroxides/Chroma-GGUF chroma-unlocked-v20/chroma-unlocked-v20-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
7.64 GiB
8.21 GB
Effective bpw
7.378
from real bytes ÷ params
Tensors
643
Header
0.04 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
414
Q6_K
228
F16
1

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.