llamaperf

Cyber-Tiel-Coder 35B-A3B / AX normal wiring / python-lru 219 input, 256 output / MTP

on M4 Pro 64GB · AX Engine

Apple hardware
Oct 13, 2026
Throughput
116.3 t/s gen
Quant
AXQ MXFP4 mixed (MLX)
MTP (Multi-Token Prediction)
on
System RAM
64 GB

Summary

User reports Cyber-Tiel-Coder-35B-A3B at 116.3 t/s on an Apple M4 Pro with 64 GiB unified memory. Setup is the AX Engine native MLX MXFP4 trunk with a protected BF16 MTP sidecar, expert streaming off, one request at a time with cold KV and no prefix reuse. The figure is the median decode rate over six measured requests on the python-lru workload at 219 input and 256 output tokens, with a range of 116.19 to 116.35 t/s; completion including TTFT was 94.37 t/s.