← Back to community benchmarks

gemma-4-26b-a4b

M5 (10c) · 32 GB · 4bit · 2026-04-12

Performance

4k

tokens

833.8

PP tok/s

33.8

TG tok/s

4913

TTFT (ms)

13.9

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	617.0	38.2	13.5 GB	view
4k	833.8	33.8	13.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	38.2	1.00×
2×	54.5	1.43×
4×	57.6	1.51×