← Back to community benchmarks

Llama-3.2-1B-Instruct

M1 (8c) · 16 GB · 4bit · 2026-03-14
Performance
1k
tokens
800.4
PP tok/s
67.8
TG tok/s
1281
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.11
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 800.4 67.8 1.3 GB current
4k 796.7 50.7 1.4 GB view
Batching Results
Batch Size TG tok/s Speedup
67.8 1.00×
115.5 1.70×
117.7 1.74×