Model comparison
AfriqueGemma-12B vs Qwythos-9B-Claude-Mythos-5-1M
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwythos-9B-Claude-Mythos-5-1M's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| AfriqueGemma-12B | Qwythos-9B-Claude-Mythos-5-1M | |
|---|---|---|
| Parameters | 12.2B | 9.4B |
| Architecture | gemma3 | qwen35 |
| Layers | 48 | 32 |
| Native context | 131,072 | 1,048,576 |
| Mixture of experts | no | no |
| Quantizations published | 24 | 16 |
| Smallest quantization | 3.05 GiB | 5.38 GiB |
| Q4_K_M | — | 10.73 GiB |
| Licence | cc-by-4.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | AfriqueGemma-12B | Qwythos-9B-Claude-Mythos-5-1M | Ratio |
|---|---|---|---|
| 4,096 | 0.72 GiB | 0.13 GiB | 5.75× |
| 8,192 | 0.97 GiB | 0.25 GiB | 3.87× |
| 16,384 | 1.47 GiB | 0.50 GiB | 2.94× |
| 32,768 | 2.47 GiB | 1.00 GiB | 2.47× |
| 65,536 | 4.47 GiB | 2.00 GiB | 2.23× |
| 131,072 | 8.47 GiB | 4.00 GiB | 2.12× |