Model comparison
gemma-3-4b-it-qat vs HyperCLOVAX-SEED-Text-Instruct-1.5B
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-3-4b-it-qat | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 3.9B | 1.6B |
| Architecture | gemma3 | llama |
| Layers | 34 | — |
| Native context | 131,072 | — |
| Mixture of experts | no | no |
| Quantizations published | 1 | 1 |
| Smallest quantization | 2.35 GiB | 1.06 GiB |
| Q4_K_M | — | 1.06 GiB |
| Licence | — | other |
KV cache by context
the term that decides long-context viability
| Context | gemma-3-4b-it-qat | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | — | — |
| 8,192 | 0.33 GiB | — | — |
| 16,384 | 0.48 GiB | — | — |
| 32,768 | 0.79 GiB | — | — |
| 65,536 | 1.42 GiB | — | — |
| 131,072 | 2.67 GiB | — | — |