---
title: LiquidAI/LFM2.5-24B-A2B-Base
url: https://recentmodel.com/models/LiquidAI/LFM2.5-24B-A2B-Base/
status: main board
published: 2026-10-09T21:13:55Z
updated: 2026-10-09T21:13:55Z
source: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-Base
---

# LiquidAI/LFM2.5-24B-A2B-Base

LFM2.5 is a new family of hybrid models designed for on-device deployment. Mixture-of-experts, 24B total, 2B active (64 experts, 4 per token). Context: 128K tokens (config). License: lfm1.0.


- **Org:** LiquidAI
- **Released:** 2026-10-09
- **Status:** main board
- **License:** lfm1.0 (restricted)
- **Parameters:** 24.0B total, 2.0B active
- **Architecture:** MoE · 64 experts, 4/token · Lfm2MoeForCausalLM
- **Context:** 131,072 tokens
- **Task:** text-generation · text
- **Signal:** 38 HF likes · 1516 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~16.1 GB (estimated): 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Mac 24GB, Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~27.2 GB (estimated): 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max)
- FP16 ~49.6 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-Base)
- [Ollama](https://ollama.com/library/lfm2.5)