← Back to community benchmarks

gemma-4-E4B-it

M4 Pro (20c) · 64 GB · 8bit · 2026-04-25
Performance
16k
tokens
987.9
PP tok/s
30.7
TG tok/s
16584
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 15.7.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 888.7 39.3 8.0 GB view
4k 1,097 36.0 8.1 GB view
8k 1,088 35.9 8.2 GB view
16k 987.9 30.7 8.4 GB current
Batching Results
Batch Size TG tok/s Speedup
39.3 1.00×
74.6 1.90×
99.2 2.52×