← Back to community benchmarks

Qwen3.6-35B-A3B

M4 (10c) · 32 GB · 4bit · 2026-04-18

Performance

1k

tokens

356.6

PP tok/s

44.6

TG tok/s

2872

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	356.6	44.6	19.2 GB	current
4k	393.0	44.1	19.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	44.6	1.00×
2×	71.3	1.60×
4×	79.2	1.78×