← Back to community benchmarks

DeepSeek-R1-0528-Qwen3-8B

M3 Max (30c) · 36 GB · 8bit · 2026-05-14

Performance

1k

tokens

546.4

PP tok/s

32.5

TG tok/s

1874

TTFT (ms)

8.9

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	546.4	32.5	8.9 GB	current
4k	556.0	30.3	9.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.5	1.00×
2×	60.7	1.87×
4×	82.1	2.53×