← Back to community benchmarks

gemma-3-4b-it-qat

M4 Pro (20c) · 48 GB · 4bit · 2026-03-09
Performance
1k
tokens
901.8
PP tok/s
34.9
TG tok/s
1137
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 901.8 34.9 3.6 GB current
4k 889.9 80.2 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
34.9 1.00×
56.9 1.63×
60.6 1.74×