← Back to community benchmarks

gemma-4-E2B-it-UD

M2 Max (30c) · 64 GB · 4bit · 2026-05-15
Performance
16k
tokens
3,044
PP tok/s
86.8
TG tok/s
5383
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,238 101.3 4.8 GB view
4k 3,243 98.6 4.9 GB view
8k 3,208 95.2 4.9 GB view
16k 3,044 86.8 5.0 GB current
32k 2,737 76.0 5.3 GB view
64k 2,259 61.9 6.0 GB view
128k 1,645 44.9 7.5 GB view