← Back to community benchmarks

gemma-4-e2b-it-5bit

M1 (7c) · 8 GB · 5bit · 2026-04-05
Performance
4k
tokens
688.1
PP tok/s
28.1
TG tok/s
5952
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
Software
oMLX v0.3.4
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 581.1 29.5 3.5 GB view
4k 688.1 28.1 3.5 GB current
8k 689.1 26.4 3.6 GB view
Batching Results
Batch Size TG tok/s Speedup
29.5 1.00×
37.6 1.27×