← Back to community benchmarks

gemma-4-E4B-it-UD

M1 Max (32c) · 32 GB · 4bit · 2026-05-25
Performance
64k
tokens
630.6
PP tok/s
24.2
TG tok/s
103919
TTFT (ms)
8.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.10
macOS macOS 14.6.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 630.6 24.2 8.3 GB current
128k 461.1 6.8 11.1 GB view