← Back to community benchmarks

gemma-4-E4B-it

M3 Pro (14c) · 18 GB · 4bit · 2026-05-03
Performance
195k
tokens
388.5
PP tok/s
11.8
TG tok/s
514755
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 18 GB
GPU Cores 14
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 769.7 27.7 7.0 GB view
4k 784.2 27.2 7.1 GB view
8k 771.6 26.6 7.3 GB view
16k 741.7 25.2 7.5 GB view
32k 688.2 22.9 7.9 GB view
64k 599.9 19.4 8.6 GB view
128k 474.1 14.9 10.3 GB view
195k 388.5 11.8 12.1 GB current
Batching Results
Batch Size TG tok/s Speedup
27.7 1.00×
54.9 1.98×
78.1 2.82×
85.7 3.09×