← Back to community benchmarks

gemma-4-e4b-it

M4 Pro (20c) · 64 GB · bf16 · 2026-04-17
Performance
16k
tokens
1,274
PP tok/s
20.1
TG tok/s
12857
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,001 24.0 14.4 GB view
4k 1,261 23.1 14.5 GB view
8k 1,297 22.5 14.6 GB view
16k 1,274 20.1 14.8 GB current
32k 1,170 16.1 15.2 GB view
64k 1,034 11.6 16.0 GB view
128k 810.0 7.6 17.8 GB view
195k 655.7 5.7 19.6 GB view