Model comparison
gemma-4-E2B-it vs Qwen3-VL-8B-Instruct-abliterated-v1
At Q4_K_M, gemma-4-E2B-it is the smaller download — 3,106,735,616 bytes against 5,027,785,792.
From the file· summed bytes, KV per layer
Side by side
| gemma-4-E2B-it | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 5.1B | 8.8B |
| Architecture | gemma4 | qwen3vl |
| Layers | 35 | — |
| Native context | 131,072 | — |
| Mixture of experts | no | no |
| Quantizations published | 18 | 48 |
| Smallest quantization | 2.13 GiB | 1.97 GiB |
| Q4_K_M | 2.89 GiB | 4.68 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gemma-4-E2B-it | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | — | — |
| 8,192 | 0.08 GiB | — | — |
| 16,384 | 0.14 GiB | — | — |
| 32,768 | 0.25 GiB | — | — |
| 65,536 | 0.46 GiB | — | — |
| 131,072 | 0.90 GiB | — | — |