← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-31
Performance
195k
tokens
565.6
PP tok/s
26.6
TG tok/s
353585
TTFT (ms)
37.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,158 74.6 25.8 GB view
16k 1,333 66.4 26.9 GB view
64k 1,003 47.7 29.7 GB view
195k 565.6 26.6 37.9 GB current
Batching Results
Batch Size TG tok/s Speedup
74.6 1.00×
115.0 1.54×
153.8 2.06×