← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-25
Performance
16k
tokens
1,658
PP tok/s
57.4
TG tok/s
9884
TTFT (ms)
27.1
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,954 45.1 25.8 GB view
4k 1,400 63.2 26.5 GB view
8k 1,534 60.2 26.6 GB view
16k 1,658 57.4 27.1 GB current
32k 2,125 64.8 28.0 GB view
64k 1,855 42.8 30.2 GB view
Batching Results
Batch Size TG tok/s Speedup
45.1 1.00×
101.2 2.24×
127.2 2.82×