← Back to community benchmarks

gemma-4-e4b-it

M1 (8c) · 16 GB · 8bit · 2026-04-06
Performance
4k
tokens
220.8
PP tok/s
10.8
TG tok/s
18548
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.4
macOS macOS 15.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 206.6 11.1 7.9 GB view
4k 220.8 10.8 8.0 GB current
Batching Results
Batch Size TG tok/s Speedup
11.1 1.00×
21.0 1.89×
29.3 2.64×