← Back to community benchmarks

gemma-4-e4b-it

M2 Max (30c) · 32 GB · bf16 · 2026-04-06
Performance
1k
tokens
870.2
PP tok/s
32.0
TG tok/s
1177
TTFT (ms)
14.4
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 870.2 32.0 14.4 GB current
4k 1,255 31.0 14.5 GB view
8k 1,355 29.8 14.6 GB view
Batching Results
Batch Size TG tok/s Speedup
32.0 1.00×
23.9 0.75×