← Back to community benchmarks

gemma-4-e4b-it

M3 (10c) · 24 GB · 8bit · 2026-04-30
Performance
8k
tokens
491.6
PP tok/s
15.2
TG tok/s
16663
TTFT (ms)
9.1
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 500.7 15.5 8.8 GB view
4k 519.8 15.6 8.9 GB view
8k 491.6 15.2 9.1 GB current
16k 205.9 7.0 9.3 GB view
Batching Results
Batch Size TG tok/s Speedup
15.5 1.00×
21.2 1.37×
42.0 2.71×