← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 64 GB · 8bit · 2026-04-28
Performance
32k
tokens
3,018
PP tok/s
39.2
TG tok/s
10858
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,053 84.9 25.7 GB view
4k 2,976 80.0 26.3 GB view
8k 3,331 73.9 26.4 GB view
16k 3,319 55.0 26.7 GB view
32k 3,018 39.2 27.5 GB current
Batching Results
Batch Size TG tok/s Speedup
84.9 1.00×
129.9 1.53×
177.4 2.09×