← Back to community benchmarks

gemma-4-E4B-it-oQ8

M1 Max (32c) · 64 GB · 8bit · 2026-05-17
Performance
4k
tokens
1,533
PP tok/s
48.4
TG tok/s
2672
TTFT (ms)
9.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,505 50.3 8.9 GB view
4k 1,533 48.4 9.1 GB current
8k 1,518 46.3 9.2 GB view
16k 1,469 42.4 9.5 GB view
32k 1,369 35.8 10.2 GB view
64k 1,195 25.6 11.0 GB view
128k 925.3 17.2 13.3 GB view
Batching Results
Batch Size TG tok/s Speedup
50.3 1.00×
88.2 1.75×
108.5 2.16×