← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-14
Performance
8k
tokens
3,636
PP tok/s
96.8
TG tok/s
2253
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,194 105.2 15.2 GB view
4k 3,397 101.1 15.7 GB view
8k 3,636 96.8 16.1 GB current
16k 3,544 89.7 16.5 GB view
32k 3,227 77.4 17.4 GB view
64k 2,527 61.5 19.4 GB view
Batching Results
Batch Size TG tok/s Speedup
105.2 1.00×
157.8 1.50×
217.9 2.07×