← Back to community benchmarks

ORACLE120

M5 Max (40c) · 128 GB · 4bit · 2026-04-27
Performance
1k
tokens
1,428
PP tok/s
99.5
TG tok/s
717
TTFT (ms)
59.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,428 99.5 59.4 GB current
4k 1,961 91.3 59.5 GB view
Batching Results
Batch Size TG tok/s Speedup
99.5 1.00×
147.7 1.48×
195.0 1.96×