← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 8bit · 2026-05-11
Performance
1k
tokens
540.7
PP tok/s
19.2
TG tok/s
1894
TTFT (ms)
7.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.5.dev1
macOS macOS 15.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 540.7 19.2 7.9 GB current
4k 607.9 18.4 8.0 GB view
Batching Results
Batch Size TG tok/s Speedup
19.2 1.00×
36.7 1.91×
58.7 3.06×