Model comparison
LFM2.5-350M vs LFM2.5-1.2B-Instruct
At Q4_K_M, LFM2.5-350M is the smaller download — 228,332,128 bytes against 730,895,168.
From the file· summed bytes, KV per layer
Side by side
| LFM2.5-350M | LFM2.5-1.2B-Instruct | |
|---|---|---|
| Parameters | 354M | 1.2B |
| Architecture | lfm2 | lfm2 |
| Layers | 16 | 16 |
| Native context | 128,000 | 128,000 |
| Mixture of experts | no | no |
| Quantizations published | 13 | 23 |
| Smallest quantization | 0.20 GiB | 0.45 GiB |
| Q4_K_M | 0.21 GiB | 0.68 GiB |
| Licence | other | other |
KV cache by context
the term that decides long-context viability
| Context | LFM2.5-350M | LFM2.5-1.2B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.05 GiB | 1.00× |
| 8,192 | 0.09 GiB | 0.09 GiB | 1.00× |
| 16,384 | 0.19 GiB | 0.19 GiB | 1.00× |
| 32,768 | 0.38 GiB | 0.38 GiB | 1.00× |
| 65,536 | 0.75 GiB | 0.75 GiB | 1.00× |
| 131,072 | 1.50 GiB | 1.50 GiB | 1.00× |