← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-04
Performance
8k
tokens
1,390
PP tok/s
71.8
TG tok/s
5895
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,099 77.5 25.8 GB view
4k 1,351 75.2 26.4 GB view
8k 1,390 71.8 26.6 GB current
16k 1,337 66.9 27.1 GB view
32k 1,212 58.8 28.0 GB view
64k 999.2 47.4 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
77.5 1.00×
118.3 1.53×
158.1 2.04×