← Back to community benchmarks

Qwen3.5-0.8B-OptiQ

M2 Max (38c) · 96 GB · 4bit · 2026-05-16

Performance

1k

tokens

617.4

PP tok/s

80.1

TG tok/s

1659

TTFT (ms)

1.7

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	617.4	80.1	1.7 GB	current
4k	1,704	75.6	2.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.1	1.00×
2×	145.5	1.82×
4×	267.2	3.34×