Model comparison
diffusiongemma-26B-A4B-it vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
At Q4_K_M, diffusiongemma-26B-A4B-it is the smaller download — 16,806,810,208 bytes against 36,545,830,912. At long context the gap widens: diffusiongemma-26B-A4B-it's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| diffusiongemma-26B-A4B-it | Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP | |
|---|---|---|
| Parameters | 25.8B | 27.8B |
| Architecture | diffusion-gemma | qwen35 |
| Layers | 30 | 64 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | yes, 128 experts | no |
| Quantizations published | 12 | 34 |
| Smallest quantization | 9.86 GiB | 10.12 GiB |
| Q4_K_M | 15.65 GiB | 34.04 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | diffusiongemma-26B-A4B-it | Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP | Ratio |
|---|---|---|---|
| 4,096 | 0.45 GiB | 0.25 GiB | 1.80× |
| 8,192 | 0.61 GiB | 0.50 GiB | 1.21× |
| 16,384 | 0.92 GiB | 1.00 GiB | 1.09× |
| 32,768 | 1.54 GiB | 2.00 GiB | 1.30× |
| 65,536 | 2.79 GiB | 4.00 GiB | 1.43× |
| 131,072 | 5.29 GiB | 8.00 GiB | 1.51× |