← Back to community benchmarks

Llama-3.2-1B-Instruct

M4 Pro (20c) · 48 GB · 4bit · 2026-03-10
Performance
1k
tokens
2,372
PP tok/s
225.4
TG tok/s
432
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,372 225.4 1.3 GB current
4k 2,779 159.7 1.5 GB view
Batching Results
Batch Size TG tok/s Speedup
225.4 1.00×
380.6 1.69×
432.5 1.92×