Model comparison
LFM2.5-VL-450M vs LFM2-VL-1.6B
At Q4_K_M, LFM2.5-VL-450M is the smaller download — 229,313,568 bytes against 730,894,016.
From the file· summed bytes, KV per layer
Side by side
| LFM2.5-VL-450M | LFM2-VL-1.6B | |
|---|---|---|
| Parameters | 449M | 1.6B |
| Architecture | lfm2 | lfm2 |
| Layers | 16 | 16 |
| Native context | 128,000 | 128,000 |
| Mixture of experts | no | no |
| Quantizations published | 9 | 26 |
| Smallest quantization | 0.20 GiB | 0.40 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-VL-450M | LFM2-VL-1.6B | 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× |