← Back to community benchmarks

gemma-4-e4b-it-mxfp8

M1 Max (32c) · 64 GB · 8bit · 2026-04-15
Performance
8k
tokens
892.2
PP tok/s
41.4
TG tok/s
9182
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.5
macOS macOS 26.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 707.2 46.8 7.8 GB view
4k 843.6 43.8 7.9 GB view
8k 892.2 41.4 8.0 GB current