← Back to community benchmarks

granite-4.1-3b

M4 Pro (16c) · 48 GB · 4bit · 2026-05-19

Performance

1k

tokens

513.8

PP tok/s

66.6

TG tok/s

1993

TTFT (ms)

2.5

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	513.8	66.6	2.5 GB	current
4k	498.3	53.1	2.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.6	1.00×
2×	88.8	1.33×
4×	102.3	1.54×