← Back to community benchmarks

Qwen3.5-0.8B

M2 Ultra (60c) · 128 GB · unknown · 2026-03-11

Performance

1k

tokens

2,043

PP tok/s

82.2

TG tok/s

501

TTFT (ms)

3.5

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 128 GB

GPU Cores 60

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	82.2	1.00×
2×	80.0	0.97×
4×	95.1	1.16×