← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 8bit · 2026-04-13
Performance
32k
tokens
553.8
PP tok/s
14.1
TG tok/s
59170
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 550.5 19.5 7.9 GB view
4k 619.2 19.0 8.0 GB view
8k 620.3 18.4 8.1 GB view
16k 601.5 16.6 8.3 GB view
32k 553.8 14.1 8.7 GB current
Batching Results
Batch Size TG tok/s Speedup
19.5 1.00×
37.5 1.92×
61.2 3.14×