How fast is AMD Radeon RX 7800 XT 16GB for local AI workloads?
AMD Radeon RX 7800 XT 16GB hits 132.0 tok/s on Phi-3 Mini, its strongest benchmarked workload (batch 1, 4096-token context, 16GB VRAM, 263W TDP). It has 4 records across 3 workloads in our database, with a MyAI Rating of 8.1/10. Llama 3 70B Q4 needs ~40GB VRAM, so check the VRAM column before assuming feasibility.