← Back to community benchmarks

Qwen3.5-0.8B

M1 Max (32c) · 64 GB · 4bit · 2026-03-10

Performance

4k

tokens

2,211

PP tok/s

174.9

TG tok/s

1853

TTFT (ms)

1.9

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	805.6	87.6	1.7 GB	view
4k	2,211	174.9	1.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.6	1.00×
2×	290.3	3.31×
4×	364.4	4.16×