← Back to community benchmarks

gemma-4-E2B-it-oQ5e

M1 Max (32c) · 64 GB · 5bit · 2026-07-13
Performance
16k
tokens
2,745
PP tok/s
76.5
TG tok/s
5969
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 3,263 81.5 3.8 GB view
16k 2,745 76.5 3.9 GB current
64k 1,841 50.8 4.9 GB view