← Back to community benchmarks

Llama-3.2-1B-Instruct

M4 (10c) · 32 GB · 4bit · 2026-03-19
Performance
1k
tokens
793.5
PP tok/s
68.2
TG tok/s
1292
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.19
macOS macOS 15.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 68.2 1.00×
2× 109.9 1.61×
4× 119.2 1.75×
8× 147.4 2.16×