Model comparison
gemma-3-270m-it-qat-q4_0-unquantized vs ced-base
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| gemma-3-270m-it-qat-q4_0-unquantized | ced-base | |
|---|---|---|
| Parameters | 268M | 86M |
| Architecture | gemma3 | ced |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 39 | 3 |
| Smallest quantization | 0.17 GiB | 0.12 GiB |
| Q4_K_M | 0.24 GiB | — |
| Licence | gemma | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gemma-3-270m-it-qat-q4_0-unquantized | ced-base | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |