← Back to community benchmarks

gemma-4-e4b-it

M5 (10c) · 32 GB · 4bit · 2026-05-06
Performance
128k
tokens
1,058
PP tok/s
13.3
TG tok/s
123844
TTFT (ms)
8.8
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,972 37.8 5.4 GB view
4k 2,081 39.5 5.5 GB view
8k 2,099 38.1 5.7 GB view
16k 1,983 34.4 5.9 GB view
32k 1,753 29.2 6.2 GB view
64k 1,403 20.6 7.0 GB view
128k 1,058 13.3 8.8 GB current
Batching Results
Batch Size TG tok/s Speedup
37.8 1.00×
79.8 2.11×