Model comparison
LFM-2.5-1.2b-Instruct-roleplay-tuned vs ced-base
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| LFM-2.5-1.2b-Instruct-roleplay-tuned | ced-base | |
|---|---|---|
| Parameters | 1.2B | 86M |
| Architecture | lfm2 | ced |
| Layers | 16 | — |
| Native context | 128,000 | — |
| Mixture of experts | no | no |
| Quantizations published | 36 | 3 |
| Smallest quantization | 0.28 GiB | 0.12 GiB |
| Q4_K_M | 0.68 GiB | — |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | LFM-2.5-1.2b-Instruct-roleplay-tuned | ced-base | 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 | — | — |