Model comparison
ideogram-4-fp8 vs FLUX.2-klein-9B
At Q4_K_M, FLUX.2-klein-9B is the smaller download — 5,027,783,648 bytes against 5,027,785,568.
From the file· summed bytes, KV per layer
Side by side
| ideogram-4-fp8 | FLUX.2-klein-9B | |
|---|---|---|
| Parameters | 9.3B | 9.1B |
| Architecture | qwen3vl | flux |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 19 | 29 |
| Smallest quantization | 4.46 GiB | 3.71 GiB |
| Q4_K_M | 4.68 GiB | 4.68 GiB |
| Licence | other | other |
KV cache by context
the term that decides long-context viability
| Context | ideogram-4-fp8 | FLUX.2-klein-9B | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |