Model comparison
OFFELLIA_Quantis vs gemma-4-E4B-it
At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 76,480,954,528.
From the file· summed bytes, KV per layer
Side by side
| OFFELLIA_Quantis | gemma-4-E4B-it | |
|---|---|---|
| Parameters | 7.6B | 8.0B |
| Architecture | qwen2vl | gemma4 |
| Layers | — | 42 |
| Native context | — | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 4 | 36 |
| Smallest quantization | 4.70 GiB | 3.30 GiB |
| Q4_K_M | 71.23 GiB | 4.64 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | OFFELLIA_Quantis | gemma-4-E4B-it | Ratio |
|---|---|---|---|
| 4,096 | — | 0.12 GiB | — |
| 8,192 | — | 0.18 GiB | — |
| 16,384 | — | 0.29 GiB | — |
| 32,768 | — | 0.51 GiB | — |
| 65,536 | — | 0.94 GiB | — |
| 131,072 | — | 1.82 GiB | — |