SPARK.Chroma_preview Q6_K

This file is exactly 7,349,776,416 bytes — 6.85 GiB / 7.35 GB at an effective 6.607 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), summed

Get it

6.85 GiB · 1 file
llama.cpp
llama-cli -hf Green-Sky/SPARK.Chroma_preview-GGUF:Q6_K

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

Hugging Face CLI
hf download Green-Sky/SPARK.Chroma_preview-GGUF SPARK.Chroma_preview-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
6.85 GiB
7.35 GB
Effective bpw
6.607
from real bytes ÷ params
Tensors
Header
GGUF metadata
SPARK.Chroma_preview Q6_K — exact size and VRAM — ossmodeldb