← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-14
Performance
16k
tokens
1,738
PP tok/s
55.2
TG tok/s
9425
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,229 69.5 14.3 GB view
4k 1,720 66.3 14.9 GB view
8k 1,802 60.5 15.1 GB view
16k 1,738 55.2 15.6 GB current
32k 1,512 46.4 16.0 GB view
64k 941.4 28.6 17.7 GB view
Batching Results
Batch Size TG tok/s Speedup
69.5 1.00×
75.9 1.09×
88.8 1.28×
104.7 1.51×