audio model · bark · macOS
BK Can I run Bark on Apple M2 (16GB)?
Yes. Bark runs on Apple M2 (16GB) at fp32 (~5 GB of ~10.5 GB usable).
Runs at fp32 using ~5 GB of ~10.5 GB usable.
- Peak memory
- ~5 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
- Quant
- fp32
How to run it
Use HF Transformers or suno-ai/bark at fp32. It is light enough to run on CPU; a GPU just makes it faster.
- Type
- Text to speech (and sound effects)
- Parameters
- 900M
- Peak memory
- ~5 GB at fp32
- License
- MIT
- Memory
- 16 GB unified
- Usable for weights
- ~10.5 GB
- Best runtime
- Ollama (llama.cpp Metal backend) / MLX
You could also run
Run Bark on other hardware
FAQ
Can Apple M2 (16GB) run Bark?
Yes. Bark runs on Apple M2 (16GB) at fp32 (~5 GB of ~10.5 GB usable).
How much memory does Bark need?
Apple M2 (16GB) has room to spare. At fp32 the realistic peak is ~5 GB of memory.
What do I use to run Bark locally?
Bark runs in HF Transformers or suno-ai/bark (among others). It runs on CPU, so no GPU is required.
Sources
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-06-15. See methodology.