Model comparison
medgemma-27b-it vs gemma-4-12B-it
At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 16,546,689,536. At long context the gap widens: gemma-4-12B-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
| medgemma-27b-it | gemma-4-12B-it | |
|---|---|---|
| Parameters | 28.8B | 12.0B |
| Architecture | gemma3 | gemma4 |
| Layers | 62 | 48 |
| Native context | 131,072 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 68 | 59 |
| Smallest quantization | 5.83 GiB | 3.92 GiB |
| Q4_K_M | 15.41 GiB | 6.63 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | medgemma-27b-it | gemma-4-12B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.92 GiB | 0.72 GiB | 1.28× |
| 8,192 | 1.23 GiB | 0.97 GiB | 1.27× |
| 16,384 | 1.86 GiB | 1.47 GiB | 1.27× |
| 32,768 | 3.11 GiB | 2.47 GiB | 1.26× |
| 65,536 | 5.61 GiB | 4.47 GiB | 1.26× |
| 131,072 | 10.61 GiB | 8.47 GiB | 1.25× |