← Back to community benchmarks

Qwen3.5-35B-A3B

M5 (10c) · 32 GB · 4bit · 2026-04-05

Performance

4k

tokens

1,085

PP tok/s

55.4

TG tok/s

3777

TTFT (ms)

19.9

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.3

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	888.0	58.1	19.2 GB	view
4k	1,085	55.4	19.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.1	1.00×
2×	89.6	1.54×
4×	107.4	1.85×