audio model · LFM · macOS
Can I run LFM3 Audio 2B on Apple M3 Pro (18GB)?
Yes. LFM3 Audio 2B runs on Apple M3 Pro (18GB) at Q8_0, audio.cpp ASR (~4.61 GB of ~12 GB usable).
Runs at Q8_0, audio.cpp ASR using ~4.61 GB of ~12 GB usable.
- Peak memory
- ~4.61 GB
- Usable on device
- ~12 GB
- Device memory
- 18 GB
- Quant
- Q8_0, audio.cpp ASR
How to run it
Use audio.cpp (experimental) at Q8_0, audio.cpp ASR. It loads as a single model and runs on a GPU.
- Type
- Speech recognition
- Parameters
- 2B
- Peak memory
- ~4.61 GB at Q8_0, audio.cpp ASR
- License
- LFM Open License v1.0
- Memory
- 18 GB unified
- Usable for weights
- ~12 GB
- Power draw
- ~70 W
- Best runtime
- Ollama (llama.cpp Metal backend) / MLX
You could also run
Run LFM3 Audio 2B on other hardware
FAQ
Can Apple M3 Pro (18GB) run LFM3 Audio 2B?
Yes. LFM3 Audio 2B runs on Apple M3 Pro (18GB) at Q8_0, audio.cpp ASR (~4.61 GB of ~12 GB usable).
How much memory does LFM3 Audio 2B need?
Apple M3 Pro (18GB) has room to spare. At Q8_0, audio.cpp ASR the realistic peak is ~4.61 GB of memory.
What do I use to run LFM3 Audio 2B locally?
LFM3 Audio 2B runs in audio.cpp (experimental). It needs a GPU.
Sources
-
apple.com · 1 source
-
blog.peddals.com · 1 source
-
developer.apple.com · 1 source
-
github.com · 3 sources
-
lmstudio.ai · 1 source
-
ollama.com · 1 source
-
support.apple.com · 3 sources
VRAM figures are sourced peak-usage anchors at the noted quant; catalog updated 2026-11-01. See methodology.