← Back to community benchmarks

gemma-3-4b-it-qat

M2 (10c) · 8 GB · 4bit · 2026-03-14
Performance
1k
tokens
196.0
PP tok/s
15.1
TG tok/s
5230
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 8 GB
GPU Cores 10
Software
oMLX v0.2.11
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 196.0 15.1 3.5 GB current
4k 180.1 22.8 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
15.1 1.00×
30.5 2.02×
33.5 2.22×