← Back to community benchmarks

gemma-4-e2b-it

M1 (8c) · 8 GB · 4bit · 2026-05-15
Performance
1k
tokens
496.7
PP tok/s
35.7
TG tok/s
2062
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 8 GB
GPU Cores 8
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 496.7 35.7 3.8 GB current
4k 755.1 34.2 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
35.7 1.00×
51.6 1.45×
55.3 1.55×