← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-06-03
Performance
64k
tokens
424.4
PP tok/s
36.8
TG tok/s
154427
TTFT (ms)
18.5
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 579.6 66.2 14.3 GB view
4k 609.8 65.1 14.9 GB view
32k 516.1 49.0 16.3 GB view
64k 424.4 36.8 18.5 GB current
Batching Results
Batch Size TG tok/s Speedup
66.2 1.00×
86.8 1.31×
99.8 1.51×