Liquid AI · 24B (2.45B active) · Mixture of Experts
Always-reasoning on-device agent MoE — 2.45B active, 131K context and stronger tool use than LFM2 Check if your GPU or Mac can run LFM2.5 24B-A2B locally — 13.4 GB min, 22.4 GB recommended.
2026-10128K context
Mixture of Experts
Total experts: 64
Active experts: 4
Active params: 2.5B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 8.2 GB | low | — |
| Q3_K_M | 3 | 11.3 GB | moderate | — |
| Q4_K_M | 4 | 12.8 GB | good | — |
| Q5_K_M | 5 | 15.9 GB | good | — |
| Q6_K | 6 | 18.9 GB | excellent | — |
| Q8_0 | 8 | 25.1 GB | excellent | — |
| F16 | 16 | 49.7 GB | lossless | — |
Can I run LFM2.5 24B-A2B locally?
- Can I run LFM2.5 24B-A2B locally?
- LFM2.5 24B-A2B needs about 13.4 GB of memory at a minimum and 22.4 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does LFM2.5 24B-A2B need?
- At Q4_K_M, LFM2.5 24B-A2B uses about 12.8 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.