← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-03-11

Performance

4k

tokens

1,703

PP tok/s

80.1

TG tok/s

2405

TTFT (ms)

36.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.7

macOS macOS 15.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,655	84.1	36.2 GB	view
4k	1,703	80.1	36.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	84.1	1.00×
2×	137.7	1.64×
4×	202.0	2.40×