← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-18

Performance

1k

tokens

2,061

PP tok/s

157.0

TG tok/s

497

TTFT (ms)

67.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,061	157.0	67.0 GB	current
4k	506.6	70.9	66.4 GB	view
8k	3,681	68.7	66.7 GB	view
16k	3,593	63.3	67.4 GB	view
32k	3,123	53.5	68.7 GB	view
64k	2,270	38.9	71.3 GB	view
128k	1,466	24.6	76.8 GB	view
195k	1,065	17.9	82.5 GB	view