Model comparison
rp-model_E2B_v5.1 vs llama-3-youko-8b
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: rp-model_E2B_v5.1's KV cache at 32K is 16.3× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| rp-model_E2B_v5.1 | llama-3-youko-8b | |
|---|---|---|
| Parameters | 5.1B | 8.0B |
| Architecture | gemma4 | llama |
| Layers | 35 | 32 |
| Native context | 131,072 | 8,192 |
| Mixture of experts | no | no |
| Quantizations published | 15 | 2 |
| Smallest quantization | 2.78 GiB | 5.34 GiB |
| Q4_K_M | — | — |
| Licence | — | llama3 |
KV cache by context
the term that decides long-context viability
| Context | rp-model_E2B_v5.1 | llama-3-youko-8b | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.50 GiB | 9.14× |
| 8,192 | 0.08 GiB | 1.00 GiB | 12.19× |
| 16,384 | 0.14 GiB | 2.00 GiB | 14.63× |
| 32,768 | 0.25 GiB | 4.00 GiB | 16.25× |
| 65,536 | 0.46 GiB | 8.00 GiB | 17.21× |
| 131,072 | 0.90 GiB | 16.00 GiB | 17.73× |