← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 64 GB · 4bit · 2026-05-28
Performance
32k
tokens
2,419
PP tok/s
74.8
TG tok/s
13548
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,209 105.2 14.3 GB view
4k 3,201 101.8 14.9 GB view
8k 3,078 97.0 15.1 GB view
16k 2,903 58.1 15.6 GB view
32k 2,419 74.8 16.5 GB current
64k 2,001 58.7 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
105.2 1.00×
164.8 1.57×
218.1 2.07×