← Back to community benchmarks

gemma-3-4b-it-5bit

M4 (10c) · 16 GB · 5bit · 2026-03-13
Performance
16k
tokens
415.3
PP tok/s
23.0
TG tok/s
39452
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 425.2 32.8 3.5 GB view
8k 424.5 28.8 3.5 GB view
16k 415.3 23.0 3.8 GB current
64k 348.2 10.5 5.6 GB view