Model comparison
polyglot-lion-0.6b vs LFM2.5-1.2B-Instruct
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| polyglot-lion-0.6b | LFM2.5-1.2B-Instruct | |
|---|---|---|
| Parameters | 782M | 1.2B |
| Architecture | qwen3vl | lfm2 |
| Layers | — | 16 |
| Native context | — | 128,000 |
| Mixture of experts | no | no |
| Quantizations published | 24 | 23 |
| Smallest quantization | 0.19 GiB | 0.45 GiB |
| Q4_K_M | — | 0.68 GiB |
| Licence | mit | other |
KV cache by context
the term that decides long-context viability
| Context | polyglot-lion-0.6b | LFM2.5-1.2B-Instruct | 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 | — |