Model comparison
Magnum-Picaro-0.7-v2-12b vs gemma-4-E4B-it
At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 7,477,204,736. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 9.9× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Magnum-Picaro-0.7-v2-12b | gemma-4-E4B-it | |
|---|---|---|
| Parameters | 12.2B | 8.0B |
| Architecture | llama | gemma4 |
| Layers | 40 | 42 |
| Native context | 1,024,000 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 45 | 36 |
| Smallest quantization | 2.79 GiB | 3.30 GiB |
| Q4_K_M | 6.96 GiB | 4.64 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Magnum-Picaro-0.7-v2-12b | gemma-4-E4B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.63 GiB | 0.12 GiB | 5.08× |
| 8,192 | 1.25 GiB | 0.18 GiB | 7.03× |
| 16,384 | 2.50 GiB | 0.29 GiB | 8.71× |
| 32,768 | 5.00 GiB | 0.51 GiB | 9.88× |
| 65,536 | 10.00 GiB | 0.94 GiB | 10.60× |
| 131,072 | 20.00 GiB | 1.82 GiB | 11.00× |