Model comparison
aya-23-8B vs Qwen3-4B
At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 5,056,982,144.
From the file· summed bytes, KV per layer
Side by side
KV cache by context
the term that decides long-context viability
| Context | aya-23-8B | Qwen3-4B | Ratio |
|---|---|---|---|
| 4,096 | — | 0.56 GiB | — |
| 8,192 | — | 1.13 GiB | — |
| 16,384 | — | 2.25 GiB | — |
| 32,768 | — | 4.50 GiB | — |
| 65,536 | — | 9.00 GiB | — |
| 131,072 | — | 18.00 GiB | — |