← Back to community benchmarks

Qwen2.5-7B-Instruct

M3 Ultra (80c) · 256 GB · unknown · 2026-03-12

Performance

1k

tokens

1,148

PP tok/s

47.6

TG tok/s

892

TTFT (ms)

28.9

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.2.9

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,148	47.6	28.9 GB	current
4k	1,512	46.0	29.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.6	1.00×
2×	51.5	1.08×
4×	100.6	2.11×