Model comparison
spoomplesmaxx-v2.1-30B vs gpt-oss-20b
At Q4_K_M, gpt-oss-20b is the smaller download — 11,624,759,488 bytes against 17,490,242,528. At long context the gap widens: gpt-oss-20b's KV cache at 32K is 10.4× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| spoomplesmaxx-v2.1-30B | gpt-oss-20b | |
|---|---|---|
| Parameters | 28.9B | 21.5B |
| Architecture | granite | gpt-oss |
| Layers | 64 | 24 |
| Native context | 131,072 | 131,072 |
| Mixture of experts | no | yes, 32 experts |
| Quantizations published | 34 | 15 |
| Smallest quantization | 5.73 GiB | 10.68 GiB |
| Q4_K_M | 16.29 GiB | 10.83 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | spoomplesmaxx-v2.1-30B | gpt-oss-20b | Ratio |
|---|---|---|---|
| 4,096 | 1.00 GiB | 0.11 GiB | 8.98× |
| 8,192 | 2.00 GiB | 0.21 GiB | 9.75× |
| 16,384 | 4.00 GiB | 0.39 GiB | 10.19× |
| 32,768 | 8.00 GiB | 0.77 GiB | 10.42× |
| 65,536 | 16.00 GiB | 1.52 GiB | 10.54× |
| 131,072 | 32.00 GiB | 3.02 GiB | 10.60× |