← Back to community benchmarks

Llama-3.2-1B-Instruct

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
1,158
PP tok/s
47.0
TG tok/s
885
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,158 47.0 1.3 GB current
4k 1,289 51.1 1.4 GB view
Batching Results
Batch Size TG tok/s Speedup
47.0 1.00×
106.3 2.26×
126.3 2.69×