Model comparison
gemma-4-12B-it-qat-q4_0-unquantized vs r1-1776-distill-llama-70b
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-4-12B-it-qat-q4_0-unquantized | r1-1776-distill-llama-70b | |
|---|---|---|
| Parameters | 12.0B | 70.6B |
| Architecture | gemma4 | llama |
| Layers | 48 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 2 | 36 |
| Smallest quantization | 6.50 GiB | 15.60 GiB |
| Q4_K_M | — | 39.60 GiB |
| Licence | apache-2.0 | mit |
KV cache by context
the term that decides long-context viability
| Context | gemma-4-12B-it-qat-q4_0-unquantized | r1-1776-distill-llama-70b | Ratio |
|---|---|---|---|
| 4,096 | 0.72 GiB | — | — |
| 8,192 | 0.97 GiB | — | — |
| 16,384 | 1.47 GiB | — | — |
| 32,768 | 2.47 GiB | — | — |
| 65,536 | 4.47 GiB | — | — |
| 131,072 | 8.47 GiB | — | — |