← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-05-18

Performance

4k

tokens

1,677

PP tok/s

104.3

TG tok/s

2442

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,300	106.9	19.3 GB	view
4k	1,677	104.3	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	106.9	1.00×
2×	179.6	1.68×