← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-14
Performance
8k
tokens
3,601
PP tok/s
96.0
TG tok/s
2275
TTFT (ms)
16.2
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 2,156 105.3 15.2 GB view
4k 3,417 101.2 15.7 GB view
8k 3,601 96.0 16.2 GB current
16k 3,554 88.5 16.5 GB view
32k 3,165 77.4 17.4 GB view
64k 2,545 61.7 19.4 GB view
Batching Results
Batch Size TG tok/s Speedup
105.3 1.00×
159.1 1.51×
218.5 2.08×