← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 64 GB · 8bit · 2026-05-11
Performance
16k
tokens
693.5
PP tok/s
41.5
TG tok/s
23625
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 656.1 46.4 25.8 GB view
4k 718.5 45.3 26.4 GB view
8k 726.7 44.1 26.6 GB view
16k 693.5 41.5 27.1 GB current
32k 611.1 37.1 28.0 GB view
64k 509.7 30.3 29.2 GB view
128k 379.2 21.7 32.7 GB view
Batching Results
Batch Size TG tok/s Speedup
46.4 1.00×
71.7 1.55×
88.2 1.90×
111.1 2.39×