Models /Granite Speech 3.3 8b /Can I run it?

Compatibility check

Can I run Granite Speech 3.3 8b on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

73 tok/sest

Usable context

262K

Memory

128 GB

Fits in memory73 tok/sest · 262K ctx

Fits in memory63 tok/sest · 262K ctx

Fits in memory42 tok/sest · 262K ctx

What is quantisation? →

Granite Speech 3.3 8b

8.6B · full specs & benchmarks →

Apple M4 Max (40-core GPU)

128 GB · everything it runs →