Models /Llama 3 8B Lunaris /Can I run it?

Compatibility check

Can I run Llama 3 8B Lunaris on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

89 tok/sest

Usable context

8K

Memory

128 GB

Fits in memory89 tok/sest · 8K ctx

Fits in memory76 tok/sest · 8K ctx

Fits in memory51 tok/sest · 8K ctx

What is quantisation? →

Llama 3 8B Lunaris

8B · full specs & benchmarks →

Apple M5 Max (40-core GPU)

128 GB · everything it runs →