← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 64 GB · 4bit · 2026-05-14
Performance
16k
tokens
2,602
PP tok/s
91.7
TG tok/s
6296
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,221 112.3 14.3 GB view
4k 2,067 103.8 14.9 GB view
8k 2,584 99.1 15.1 GB view
16k 2,602 91.7 15.6 GB current
32k 2,450 78.7 16.5 GB view
64k 2,027 59.9 18.5 GB view
128k 1,408 38.9 22.7 GB view
Batching Results
Batch Size TG tok/s Speedup
112.3 1.00×
159.1 1.42×
193.5 1.72×