← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 128 GB · 6bit · 2026-03-09

Performance

8k

tokens

1,355

PP tok/s

63.8

TG tok/s

6044

TTFT (ms)

28.5

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,355	63.8	28.5 GB	current
16k	1,216	61.1	28.9 GB	view
32k	944.5	49.2	29.7 GB	view
64k	727.1	39.5	31.4 GB	view