← Back to community benchmarks

Qwen3.5-9B

M1 Max (24c) · 64 GB · 8bit · 2026-03-09

Performance

4k

tokens

239.7

PP tok/s

34.0

TG tok/s

17091

TTFT (ms)

11.0

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.2.6

macOS macOS 15.7.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	238.4	35.8	10.7 GB	view
4k	239.7	34.0	11.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.8	1.00×
2×	53.4	1.49×
4×	59.5	1.66×