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

Can I run Llama 3.2 3B Instruct on Radeon RX 6600?

Yes — it runs.best quant:
Decode speed
75 tok/sest
Usable context
66K
Memory
8 GB
Fits in memory75 tok/sest · 66K ctx
Fits in memory64 tok/sest · 66K ctx
Fits in memory43 tok/sest · 66K ctx
What is quantisation? →
Llama 3.2 3B Instruct
3.2B · full specs & benchmarks →
Radeon RX 6600
8 GB · everything it runs →