← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-09
Performance
16k
tokens
3,560
PP tok/s
87.7
TG tok/s
4603
TTFT (ms)
16.6
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 2,216 105.3 15.2 GB view
4k 3,250 97.5 15.8 GB view
8k 3,583 96.3 16.0 GB view
16k 3,560 87.7 16.6 GB current
32k 3,225 76.3 17.4 GB view
64k 2,563 59.1 19.4 GB view
Batching Results
Batch Size TG tok/s Speedup
105.3 1.00×
153.6 1.46×
218.0 2.07×