Models /Nemotron Speech Streaming en 0.6b /Can I run it?

Compatibility check

Can I run Nemotron Speech Streaming en 0.6b on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

1051 tok/sest

Usable context

262K

Memory

128 GB

Fits in memory1051 tok/sest · 262K ctx

Fits in memory896 tok/sest · 262K ctx

Fits in memory600 tok/sest · 262K ctx

What is quantisation? →

Nemotron Speech Streaming en 0.6b

0.6B · full specs & benchmarks →

Apple M4 Max (40-core GPU)

128 GB · everything it runs →