← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-04-29

Performance

64k

tokens

1,078

PP tok/s

59.6

TG tok/s

60798

TTFT (ms)

41.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,530	307.4	36.7 GB	view
4k	958.9	98.1	36.2 GB	view
8k	1,818	94.2	36.5 GB	view
16k	1,704	87.1	37.1 GB	view
32k	1,431	74.4	38.5 GB	view
64k	1,078	59.6	41.2 GB	current