← Back to community benchmarks

DeepSeek-R1-0528-Qwen3-8B

M4 Pro (16c) · 48 GB · 4bit · 2026-03-10

Performance

4k

tokens

335.6

PP tok/s

42.5

TG tok/s

12204

TTFT (ms)

5.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.7

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	350.0	49.4	5.0 GB	view
4k	335.6	42.5	5.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	49.4	1.00×
2×	76.4	1.55×
4×	81.8	1.66×