← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-06-01
Performance
1k
tokens
1,747
PP tok/s
68.8
TG tok/s
586
TTFT (ms)
25.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,747 68.8 25.8 GB current
4k 2,659 63.2 26.4 GB view
8k 2,944 67.2 26.6 GB view
16k 2,683 61.3 27.1 GB view
32k 2,251 53.1 28.0 GB view
64k 1,695 40.2 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
68.8 1.00×
102.9 1.50×
121.3 1.76×