Text model · LFM
LF Can I run LFM2.5 8B-A1B? Pick your device.
LFM2.5 8B-A1B is a 8.3B MoE (1.5B active) model. At Q4_K_M the weights are ~4.8 GB; with KV cache and runtime overhead, budget ~6.3 GB. Select your hardware below to see the full compatibility breakdown.
NVIDIA GPUs
- Nvidia GeForce RTX 2060 (6GB) No
- Nvidia GeForce RTX 3060 Ti (8GB) Tight
- Nvidia GeForce GTX 1070 (8GB) Tight
- Nvidia GeForce RTX 3060 (12GB) Yes
- Nvidia GeForce RTX 4070 (12GB) Yes
- Nvidia GeForce RTX 5070 (12GB) Yes
- Nvidia GeForce RTX 4060 Ti (16GB) Yes
- Nvidia GeForce RTX 4080 (16GB) Yes
- Nvidia GeForce RTX 5080 (16GB) Yes
- Nvidia GeForce RTX 5070 Ti (16GB) Yes
- Nvidia GeForce RTX 5060 Ti (16GB) Yes
- Nvidia GeForce RTX 4090 (24GB) Yes
- Nvidia GeForce RTX 3090 (24GB) Yes
- Nvidia GeForce RTX 5090 (32GB) Yes
- Nvidia DGX Spark (128GB) Yes
Apple Silicon Macs
- Apple M1 (8GB) No
- Apple M2 (16GB) Yes
- Apple M4 (16GB) Yes
- Apple M5 (16GB) Yes
- Apple M3 Pro (18GB) Yes
- Apple M4 (24GB) Yes
- Apple M4 Pro (24GB) Yes
- Apple M5 (32GB) Yes
- Apple M4 Pro (48GB) Yes
- Apple M5 Pro (48GB) Yes
- Apple M4 Max (64GB) Yes
- Apple M4 Max (128GB) Yes
- Apple M5 Max (128GB) Yes
- Apple M3 Ultra (256GB) Yes
RAM-only laptops
iPhone & iPad
Android
AMD GPUs
Memory figures are estimates. See methodology.