Model comparison
granite-4.0-1b vs Wan2.1-T2V-1.3B
At Q4_K_M, Wan2.1-T2V-1.3B is the smaller download — 982,716,640 bytes against 1,023,645,440.
From the file· summed bytes, KV per layer
Side by side
| granite-4.0-1b | Wan2.1-T2V-1.3B | |
|---|---|---|
| Parameters | 1.6B | 1.4B |
| Architecture | granite | qwen35 |
| Layers | 40 | — |
| Native context | 131,072 | — |
| Mixture of experts | no | no |
| Quantizations published | 35 | 31 |
| Smallest quantization | 0.44 GiB | 0.61 GiB |
| Q4_K_M | 0.95 GiB | 0.92 GiB |
| Licence | apache-2.0 | — |
KV cache by context
the term that decides long-context viability
| Context | granite-4.0-1b | Wan2.1-T2V-1.3B | Ratio |
|---|---|---|---|
| 4,096 | 0.31 GiB | — | — |
| 8,192 | 0.63 GiB | — | — |
| 16,384 | 1.25 GiB | — | — |
| 32,768 | 2.50 GiB | — | — |
| 65,536 | 5.00 GiB | — | — |
| 131,072 | 10.00 GiB | — | — |