← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M5 Max (40c) · 128 GB · 4bit · 2026-05-12
Performance
64k
tokens
2,597
PP tok/s
61.5
TG tok/s
25234
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,232 105.1 15.2 GB view
4k 3,315 101.6 15.7 GB view
8k 3,694 96.3 16.2 GB view
16k 3,657 88.8 16.5 GB view
32k 3,252 77.1 17.4 GB view
64k 2,597 61.5 19.4 GB current
Batching Results
Batch Size TG tok/s Speedup
105.1 1.00×
154.3 1.47×
216.6 2.06×