← Back to community benchmarks

gemma-4-E4B-it

M5 (10c) · 32 GB · 8bit · 2026-06-05
Performance
195k
tokens
766.5
PP tok/s
9.0
TG tok/s
260920
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,699 22.3 8.8 GB view
4k 1,936 20.9 8.9 GB view
8k 1,868 20.1 9.0 GB view
16k 1,765 18.4 9.3 GB view
32k 1,544 17.5 9.6 GB view
64k 1,269 14.7 10.9 GB view
128k 949.0 10.9 13.2 GB view
195k 766.5 9.0 16.1 GB current
Batching Results
Batch Size TG tok/s Speedup
22.3 1.00×
44.9 2.01×
75.4 3.38×
149.6 6.71×