← Back to community benchmarks

gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking-mxfp8

M4 Max (40c) · 128 GB · 8bit · 2026-05-29
Performance
32k
tokens
1,950
PP tok/s
48.0
TG tok/s
16801
TTFT (ms)
10.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,153 62.4 8.9 GB view
4k 2,131 61.1 8.9 GB view
8k 2,247 58.4 9.1 GB view
16k 2,147 54.5 9.4 GB view
32k 1,950 48.0 10.1 GB current
64k 1,648 37.3 10.9 GB view
128k 1,337 26.8 13.2 GB view
Batching Results
Batch Size TG tok/s Speedup
62.4 1.00×
101.9 1.63×
142.3 2.28×
154.9 2.48×