Models /Llama 3.2 3B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 3B Instruct on Ryzen AI Max+ 395 (Radeon 8060S)?

Yes — it runs.best quant:

Decode speed

86 tok/sest

Usable context

131K

Memory

128 GB

Fits in memory86 tok/sest · 131K ctx

Fits in memory73 tok/sest · 131K ctx

Fits in memory49 tok/sest · 131K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

Ryzen AI Max+ 395 (Radeon 8060S)

128 GB · everything it runs →