← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-14
Performance
32k
tokens
1,234
PP tok/s
61.1
TG tok/s
26555
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,188 77.3 25.8 GB view
4k 1,402 75.3 26.3 GB view
8k 1,416 72.6 26.8 GB view
16k 1,361 68.6 27.1 GB view
32k 1,234 61.1 28.0 GB current
64k 1,025 50.6 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
77.3 1.00×
120.4 1.56×
162.9 2.11×
204.7 2.65×