# LFM2 24B-A2B: RAM and VRAM requirements

> LFM2 24B-A2B is a 24B LFM model (Mixture-of-Experts, 2.3B active per token). At Q4_K_M it needs about **15.4 GB** to run and fits **15 of 40** tracked devices. Minimum to run: Apple M4 (24GB).

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 13.43 GB | ~15.4 GB |
| Q8_0 | 23.61 GB | ~25.6 GB |
| FP16 | 44.42 GB | ~46.4 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): Yes, it runs
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs (room for Q8_0)
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs (room for FP16)

Full table of all 40 devices: https://localmodel.run/model/lfm2-24b-a2b

## How to run
Quickest path: `ollama run lfm2:24b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 24B (MoE, 2.3B active per token)
- Default context: 32k tokens
- License: LFM Open License v1.0 (commercial use: conditional)
- Released: 2026-02
- HuggingFace: 3,687 downloads/mo, 340 likes

## FAQ
### How much VRAM or RAM does LFM2 24B-A2B need?
About 15.4 GB at Q4_K_M (weights 13.43 GB + KV cache + overhead) at a 4k context. Budget ~25.6 GB for Q8_0.
### Can LFM2 24B-A2B run on a laptop?
LFM2 24B-A2B is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use LFM2 24B-A2B commercially?
Conditionally: LFM Open License: free under $10M revenue; larger companies need a commercial license..

Sources: https://huggingface.co/LiquidAI/LFM2-24B-A2B, https://huggingface.co/LiquidAI/LFM2-24B-A2B-GGUF, https://ollama.com/library/lfm2/tags
More: https://localmodel.run/model/lfm2-24b-a2b