Model comparison
Chroma1-Flash vs FLUX.1-dev
At Q4_K_M, Chroma1-Flash is the smaller download — 5,566,533,792 bytes against 6,931,817,760.
From the file· summed bytes, KV per layer
Side by side
| Chroma1-Flash | FLUX.1-dev | |
|---|---|---|
| Parameters | 8.9B | 11.9B |
| Architecture | flux | flux |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 13 | 37 |
| Smallest quantization | 3.18 GiB | 3.75 GiB |
| Q4_K_M | 5.18 GiB | 6.46 GiB |
| Licence | apache-2.0 | other |
KV cache by context
the term that decides long-context viability
| Context | Chroma1-Flash | FLUX.1-dev | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |