← Back to community benchmarks

Llama-3.2-1B-Instruct

M2 Pro (16c) · 16 GB · 4bit · 2026-04-16
Performance
1k
tokens
1,713
PP tok/s
178.6
TG tok/s
599
TTFT (ms)
1.4
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.3.5
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,713 178.6 1.4 GB current
4k 1,908 129.0 1.5 GB view
Batching Results
Batch Size TG tok/s Speedup
178.6 1.00×
260.8 1.46×