Model comparison
gemma-4-12B-it vs glm-4v-9b
At Q4_K_M, glm-4v-9b is the smaller download — 6,166,574,560 bytes against 7,121,861,440.
From the file· summed bytes, KV per layer
Side by side
| gemma-4-12B-it | glm-4v-9b | |
|---|---|---|
| Parameters | 12.0B | 13.9B |
| Architecture | gemma4 | glm4 |
| Layers | 48 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 59 | 14 |
| Smallest quantization | 3.92 GiB | 3.73 GiB |
| Q4_K_M | 6.63 GiB | 5.74 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gemma-4-12B-it | glm-4v-9b | Ratio |
|---|---|---|---|
| 4,096 | 0.72 GiB | — | — |
| 8,192 | 0.97 GiB | — | — |
| 16,384 | 1.47 GiB | — | — |
| 32,768 | 2.47 GiB | — | — |
| 65,536 | 4.47 GiB | — | — |
| 131,072 | 8.47 GiB | — | — |