← Back to community benchmarks

DeepSeek-R1-0528-Qwen3-8B

M2 Max (30c) · 64 GB · 4bit · 2026-04-28

Performance

4k

tokens

312.9

PP tok/s

48.1

TG tok/s

13092

TTFT (ms)

5.5

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	311.4	58.8	5.0 GB	view
4k	312.9	48.1	5.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.8	1.00×
2×	69.0	1.17×
4×	75.4	1.28×