3models tracked · ranked by intelligence, speed & price
LiquidAI's smartest model is LFM2-24B-A2B (10.5 on the Intelligence Index), its fastest is LFM2.5-1.2B-Thinking (free) at 122 tokens/sec, and its cheapest is LFM2-24B-A2B at $0.030 per million input tokens. All 3 LiquidAI models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| lfm-2-24b-a2b | 10.5 | 60 | 200ms | $0.030 | 128K |
| lfm-2.5-1.2b-thinking:free Reasoning | 8.1 | 122 | 367ms | Free | 33K |
| lfm-2.5-1.2b-instruct:free | 8.0 | 92 | 359ms | Free | 33K |