← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 4bit · 2026-04-12
User comment500
Performance
195k
tokens
274.4
PP tok/s
0.4
TG tok/s
728786
TTFT (ms)
11.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 555.4 22.2 6.0 GB view
4k 624.1 21.7 6.1 GB view
8k 624.1 19.3 6.2 GB view
16k 604.7 12.3 6.3 GB view
32k 559.0 8.1 6.8 GB view
64k 466.7 1.4 7.6 GB view
128k 356.7 0.3 9.4 GB view
195k 274.4 0.4 11.2 GB current
Batching Results
Batch Size TG tok/s Speedup
22.2 1.00×
41.8 1.88×
66.4 2.99×