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

Can I run Llama 3.2 3B Instruct on Radeon RX 9070?

Yes — it runs.best quant:
Decode speed
214 tok/sest
Usable context
131K
Memory
16 GB
Fits in memory214 tok/sest · 131K ctx
Fits in memory183 tok/sest · 131K ctx
Fits in memory122 tok/sest · 131K ctx
What is quantisation? →
Llama 3.2 3B Instruct
3.2B · full specs & benchmarks →
Radeon RX 9070
16 GB · everything it runs →