← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 8bit · 2026-04-05
Performance
32k
tokens
517.4
PP tok/s
14.7
TG tok/s
63336
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.4
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 525.2 19.4 7.9 GB view
4k 600.8 17.8 8.0 GB view
8k 597.7 18.4 8.1 GB view
16k 578.2 17.0 8.3 GB view
32k 517.4 14.7 8.7 GB current
64k 439.7 13.0 9.6 GB view
128k 343.2 9.2 11.3 GB view