← Back to community benchmarks

translategemma-4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-03-20
Performance
64k
tokens
4,226
PP tok/s
56.5
TG tok/s
15509
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.20.dev1
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,446 160.4 2.9 GB view
4k 3,949 150.1 3.1 GB view
8k 4,919 135.8 3.2 GB view
32k 4,748 84.2 4.1 GB view
64k 4,226 56.5 5.3 GB current
Batching Results
Batch Size TG tok/s Speedup
160.4 1.00×
276.6 1.72×
395.9 2.47×
448.5 2.80×