← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-12
Performance
8k
tokens
3,648
PP tok/s
96.9
TG tok/s
2246
TTFT (ms)
16.2
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,246 102.9 15.2 GB view
4k 3,341 98.6 15.7 GB view
8k 3,648 96.9 16.2 GB current
16k 3,616 89.4 16.5 GB view
32k 3,265 77.6 17.4 GB view
64k 2,592 61.3 19.4 GB view
Batching Results
Batch Size TG tok/s Speedup
102.9 1.00×
155.2 1.51×
218.3 2.12×