← Back to community benchmarks

translategemma-4b-it

M4 Pro (16c) · 64 GB · 4bit · 2026-03-11

Performance

4k

tokens

642.0

PP tok/s

78.1

TG tok/s

6382

TTFT (ms)

3.1

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.8

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	589.6	80.7	2.9 GB	view
4k	642.0	78.1	3.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.7	1.00×
2×	130.0	1.61×
4×	140.5	1.74×