Model comparison
granite-4.1-8b vs Qwen3-VL-8B-Instruct-abliterated-v1
At Q4_K_M, Qwen3-VL-8B-Instruct-abliterated-v1 is the smaller download — 5,027,785,792 bytes against 5,347,914,400.
From the file· summed bytes, KV per layer
Side by side
| granite-4.1-8b | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 8.8B | 8.8B |
| Architecture | — | qwen3vl |
| Layers | 40 | — |
| Native context | 131,072 | — |
| Mixture of experts | no | no |
| Quantizations published | 30 | 48 |
| Smallest quantization | 3.05 GiB | 1.97 GiB |
| Q4_K_M | 4.98 GiB | 4.68 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | granite-4.1-8b | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.63 GiB | — | — |
| 8,192 | 1.25 GiB | — | — |
| 16,384 | 2.50 GiB | — | — |
| 32,768 | 5.00 GiB | — | — |
| 65,536 | 10.00 GiB | — | — |
| 131,072 | 20.00 GiB | — | — |