← Back to community benchmarks

gemma-4-e2b-it

M1 (7c) · 16 GB · 4bit · 2026-04-06
Performance
4k
tokens
668.1
PP tok/s
33.7
TG tok/s
6131
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 509.4 35.4 2.9 GB view
4k 668.1 33.7 3.0 GB current
Batching Results
Batch Size TG tok/s Speedup
35.4 1.00×
46.3 1.31×
50.0 1.41×