Models /R1 Distill Llama 70B /Can I run it?

Compatibility check

Can I run R1 Distill Llama 70B on Apple M3 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

7 tok/sest

Usable context

8K

Memory

128 GB

Fits in memory7 tok/sest · 8K ctx

Fits in memory6 tok/sest · 8K ctx

Fits in memory4 tok/sest · 8K ctx

What is quantisation? →

R1 Distill Llama 70B

70.6B · full specs & benchmarks →

Apple M3 Max (40-core GPU)

128 GB · everything it runs →