Model comparison

SPARK.Chroma_preview vs FLUX.2-klein-9B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

SPARK.Chroma_previewFLUX.2-klein-9B
Parameters8.9B9.1B
Architectureflux
Layers
Native context
Mixture of expertsnono
Quantizations published529
Smallest quantization4.71 GiB3.71 GiB
Q4_K_M4.68 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextSPARK.Chroma_previewFLUX.2-klein-9BRatio
4,096
8,192
16,384
32,768
65,536
131,072
SPARK.Chroma_preview vs FLUX.2-klein-9B — size, memory and hardware fit — ossmodeldb