LLMap
Models /Whisper Large v3 /Can I run it?
Compatibility check

Can I run Whisper Large v3 on Radeon RX 9070?

Yes — it runs.best quant:
Decode speed
458 tok/sest
Usable context
262K
Memory
16 GB
Fits in memory458 tok/sest · 262K ctx
Fits in memory390 tok/sest · 262K ctx
Fits in memory261 tok/sest · 262K ctx
What is quantisation? →
Whisper Large v3
1.5B · full specs & benchmarks →
Radeon RX 9070
16 GB · everything it runs →