← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Max (38c) · 64 GB · 4bit · 2026-05-02
Performance
195k
tokens
326.5
PP tok/s
15.6
TG tok/s
612613
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 547.4 70.4 14.3 GB view
4k 618.1 66.0 14.9 GB view
8k 627.2 62.0 15.1 GB view
16k 611.8 56.0 15.6 GB view
32k 573.7 46.5 16.5 GB view
64k 504.6 34.5 17.7 GB view
128k 400.6 21.8 21.2 GB view
195k 326.5 15.6 25.0 GB current
Batching Results
Batch Size TG tok/s Speedup
70.4 1.00×
95.4 1.36×
113.5 1.61×