← Back to community benchmarks

FuseO1-DeepSeekR1-Qwen2.5-Coder-14B-Preview-mixed_3_6

M4 Pro (20c) · 64 GB · 4bit · 2026-04-28

Performance

1k

tokens

246.2

PP tok/s

32.5

TG tok/s

4159

TTFT (ms)

7.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	246.2	32.5	7.2 GB	current
4k	244.2	28.7	7.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.5	1.00×
2×	42.6	1.31×
4×	41.9	1.29×