← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-25
Performance
32k
tokens
2,118
PP tok/s
60.8
TG tok/s
15475
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,144 85.2 25.8 GB view
4k 1,881 81.7 26.4 GB view
8k 2,146 78.2 26.6 GB view
16k 2,280 71.7 27.1 GB view
32k 2,118 60.8 28.0 GB current
64k 1,700 44.2 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
85.2 1.00×
88.8 1.04×
115.0 1.35×