Models /Hermes 3 70B Instruct /Can I run it?

Compatibility check

Can I run Hermes 3 70B Instruct on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

10 tok/sest

Usable context

131K

Memory

128 GB

Fits in memory10 tok/sest · 131K ctx

Fits in memory9 tok/sest · 66K ctx

Fits in memory6 tok/sest · 33K ctx

What is quantisation? →

Hermes 3 70B Instruct

70.6B · full specs & benchmarks →

Apple M5 Max (40-core GPU)

128 GB · everything it runs →