← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-14
Performance
32k
tokens
3,225
PP tok/s
77.9
TG tok/s
10162
TTFT (ms)
17.4
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 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,217 102.8 15.2 GB view
4k 3,409 101.4 15.7 GB view
8k 3,708 97.5 16.2 GB view
16k 3,579 90.0 16.5 GB view
32k 3,225 77.9 17.4 GB current
64k 2,545 61.3 19.4 GB view
Batching Results
Batch Size TG tok/s Speedup
102.8 1.00×
160.2 1.56×
219.1 2.13×