Model comparison
ThinkingCap-Qwen3.6-27B vs gemma-4-12B-it
At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 16,810,713,056. At long context the gap widens: ThinkingCap-Qwen3.6-27B's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| ThinkingCap-Qwen3.6-27B | gemma-4-12B-it | |
|---|---|---|
| Parameters | 27.4B | 12.0B |
| Architecture | qwen35 | gemma4 |
| Layers | 64 | 48 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 28 | 59 |
| Smallest quantization | 9.30 GiB | 3.92 GiB |
| Q4_K_M | 15.66 GiB | 6.63 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | ThinkingCap-Qwen3.6-27B | gemma-4-12B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.72 GiB | 2.87× |
| 8,192 | 0.50 GiB | 0.97 GiB | 1.94× |
| 16,384 | 1.00 GiB | 1.47 GiB | 1.47× |
| 32,768 | 2.00 GiB | 2.47 GiB | 1.23× |
| 65,536 | 4.00 GiB | 4.47 GiB | 1.12× |
| 131,072 | 8.00 GiB | 8.47 GiB | 1.06× |