← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-06-03
Performance
32k
tokens
516.1
PP tok/s
49.0
TG tok/s
63490
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 32,768
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 current
64k 424.4 36.8 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
66.2 1.00×
86.8 1.31×
99.8 1.51×