← Back to community benchmarks

gemma-4-E4B-it

M1 Max (32c) · 64 GB · 8bit · 2026-04-25
Performance
16k
tokens
889.8
PP tok/s
30.7
TG tok/s
18413
TTFT (ms)
9.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 893.6 38.1 9.0 GB view
4k 917.4 36.3 9.1 GB view
8k 910.2 34.4 9.1 GB view
16k 889.8 30.7 9.3 GB current
32k 847.0 25.2 9.9 GB view
Batching Results
Batch Size TG tok/s Speedup
38.1 1.00×
56.6 1.49×
80.6 2.12×