Models /GLM ASR Nano 2512 /Can I run it?

Compatibility check

Can I run GLM ASR Nano 2512 on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

274 tok/sest

Usable context

262K

Memory

128 GB

Fits in memory274 tok/sest · 262K ctx

Fits in memory234 tok/sest · 262K ctx

Fits in memory156 tok/sest · 262K ctx

What is quantisation? →

GLM ASR Nano 2512

2.3B · full specs & benchmarks →

Apple M4 Max (40-core GPU)

128 GB · everything it runs →