Model comparison
gpt2 vs LFM2.5-230M
At Q4_K_M, gpt2 is the smaller download — 112,858,624 bytes against 153,406,048.
From the file· summed bytes, KV per layer
Side by side
| gpt2 | LFM2.5-230M | |
|---|---|---|
| Parameters | 137M | 230M |
| Architecture | gpt2 | lfm2 |
| Layers | 12 | 14 |
| Native context | — | 128,000 |
| Mixture of experts | no | no |
| Quantizations published | 49 | 25 |
| Smallest quantization | 0.06 GiB | 0.10 GiB |
| Q4_K_M | 0.11 GiB | 0.14 GiB |
| Licence | — | other |
KV cache by context
the term that decides long-context viability
| Context | gpt2 | LFM2.5-230M | Ratio |
|---|---|---|---|
| 4,096 | — | 0.05 GiB | — |
| 8,192 | — | 0.09 GiB | — |
| 16,384 | — | 0.19 GiB | — |
| 32,768 | — | 0.38 GiB | — |
| 65,536 | — | 0.75 GiB | — |
| 131,072 | — | 1.50 GiB | — |