← Back to community benchmarks

gemma-4-e4b-mxfp8

M2 Pro (16c) · 16 GB · 8bit · 2026-04-03
Performance
32k
tokens
484.2
PP tok/s
15.9
TG tok/s
67676
TTFT (ms)
9.6
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.3.2
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 484.2 15.9 9.6 GB current
64k 438.6 11.0 10.3 GB view