Compatibility check
Can I run Llama 3 8B Lunaris on Apple M2 (8-core GPU, 8GB unified)?
Partially — with CPU offload.best quant:
5 GB of weights, plus 1.6 GB for the software that runs it and the smallest conversation it can hold, comes to 6.6 GB against the 6 GB this 8 GB device leaves free.
Decode speed
—
Usable context
—
Memory
8 GB
Spills to system RAM
Spills to system RAM
Too large
Plan B — rent it
Llama 3 8B Lunaris is hosted by 4 providers from $0.050 per 1M output tokens (OpenRouter).Compare providers →
