← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · unknown · 2026-04-13
Performance
32k
tokens
1,215
PP tok/s
20.8
TG tok/s
26961
TTFT (ms)
49.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,105 32.2 47.7 GB view
4k 1,280 31.3 48.2 GB view
8k 1,352 29.5 48.3 GB view
16k 1,306 25.5 48.7 GB view
32k 1,215 20.8 49.5 GB current
64k 973.7 14.9 51.2 GB view
Batching Results
Batch Size TG tok/s Speedup
32.2 1.00×
31.5 0.98×
50.4 1.57×
69.3 2.15×