← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-12
Performance
16k
tokens
3,616
PP tok/s
89.4
TG tok/s
4531
TTFT (ms)
16.5
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 16,384
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 view
16k 3,616 89.4 16.5 GB current
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×