Liquid AI · 24B (2.3B active) · 專家混合（MoE）
Hybrid MoE with convolution+attention layers — 2.3B active 看看你的 GPU 或 Mac 跑不跑得動 LFM2 24B——最低 13.4 GB，建議 22.4 GB。
2025-1132K context
專家混合（MoE）
專家總数： 64
啟用專家： 4
啟用参数： 2.3B
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| 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 | — |
關於這個模型
LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.
- Best-in-class efficiency: A 24B MoE model with only 2B active parameters per token, fitting in 32 GB of RAM for deployment on consumer laptops and desktops.
- Fast edge inference: 112 tok/s decode on AMD CPU, 293 tok/s on H100. Fits in 32B GB of RAM.
- Predictable scaling: Quality improves log-linearly from 350M to 24B total parameters, confirming the LFM2 hybrid architecture scales reliably across nearly two orders of magnitude.
Can I run LFM2 24B locally?
- Can I run LFM2 24B locally?
- LFM2 24B 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 24B need?
- At Q4_K_M, LFM2 24B uses about 12.8 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.