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

Can I run Whisper Large v3 Turbo on Radeon RX 9070?

Yes — it runs.best quant:
Decode speed
858 tok/sest
Usable context
262K
Memory
16 GB
Fits in memory858 tok/sest · 262K ctx
Fits in memory731 tok/sest · 262K ctx
Fits in memory489 tok/sest · 262K ctx
What is quantisation? →
Whisper Large v3 Turbo
0.8B · full specs & benchmarks →
Radeon RX 9070
16 GB · everything it runs →