← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 64 GB · 4bit · 2026-06-02
Performance
64k
tokens
519.9
PP tok/s
36.6
TG tok/s
126052
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.0
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 695.1 64.5 14.3 GB view
4k 747.0 62.3 15.0 GB view
8k 741.1 59.7 15.3 GB view
16k 705.6 55.5 15.8 GB view
64k 519.9 36.6 18.3 GB current
Batching Results
Batch Size TG tok/s Speedup
64.5 1.00×
84.4 1.31×
109.2 1.69×