- throughput:
- 3029.0 t/s pp
User built custom w8a8 kernels for M5 MacBook Air. Baseline prefill 2193 tps, improved to 3029 tps for 130k tokens. Also mentions llama.cpp for Macs.
M5 32GB
APPLE · 32GB unified memory · 1 report
This page is thin (1 of 3 reports needed for indexing). Help fill it in.