← Back to community benchmarks

gemma-4-e4b-it

M4 Pro (16c) · 24 GB · 8bit · 2026-05-16
Performance
64k
tokens
793.7
PP tok/s
27.6
TG tok/s
82574
TTFT (ms)
10.5
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 997.9 41.0 9.0 GB view
4k 1,020 38.2 9.1 GB view
8k 996.6 39.9 9.2 GB view
16k 972.9 36.9 9.5 GB view
32k 902.2 33.7 10.2 GB view
64k 793.7 27.6 10.5 GB current
Batching Results
Batch Size TG tok/s Speedup
41.0 1.00×
78.5 1.91×
95.5 2.33×
102.8 2.51×