← Back to community benchmarks

Qwen3.5-0.8B

M2 Max (30c) · 32 GB · 8bit · 2026-03-10

Performance

4k

tokens

3,365

PP tok/s

211.6

TG tok/s

1217

TTFT (ms)

2.2

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.2.7

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	3,360	235.0	2.0 GB	view
4k	3,365	211.6	2.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	235.0	1.00×
2×	407.9	1.74×
4×	531.5	2.26×
8×	530.8	2.26×