← Back to community benchmarks

gemma-4-e2b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-18
Performance
4k
tokens
3,150
PP tok/s
95.1
TG tok/s
1300
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,079 97.3 4.0 GB view
4k 3,150 95.1 4.0 GB current
Batching Results
Batch Size TG tok/s Speedup
97.3 1.00×
141.6 1.46×
181.0 1.86×