← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmxfp8

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-28

Performance

1k

tokens

2,142

PP tok/s

321.0

TG tok/s

478

TTFT (ms)

35.7

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,142	321.0	35.7 GB	current
4k	907.6	78.4	35.2 GB	view
8k	2,602	74.9	35.5 GB	view