Model comparison
gemma-2-2b-it-abliterated vs Qwen3-VL-8B-Instruct-abliterated-v1
At Q4_K_M, gemma-2-2b-it-abliterated is the smaller download — 1,708,582,784 bytes against 5,027,785,792.
From the file· summed bytes, KV per layer
Side by side
| gemma-2-2b-it-abliterated | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 2.6B | 8.8B |
| Architecture | gemma2 | qwen3vl |
| Layers | 26 | — |
| Native context | 8,192 | — |
| Mixture of experts | no | no |
| Quantizations published | 29 | 48 |
| Smallest quantization | 1.15 GiB | 1.97 GiB |
| Q4_K_M | 1.59 GiB | 4.68 GiB |
| Licence | gemma | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gemma-2-2b-it-abliterated | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.41 GiB | — | — |
| 8,192 | 0.63 GiB | — | — |
| 16,384 | 1.04 GiB | — | — |
| 32,768 | 1.85 GiB | — | — |
| 65,536 | 3.48 GiB | — | — |
| 131,072 | 6.73 GiB | — | — |