← Back to community benchmarks

Llama-3.2-3B-Instruct

M2 Max (38c) · 32 GB · 4bit · 2026-03-12
Performance
1k
tokens
1,222
PP tok/s
127.2
TG tok/s
839
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.2.8
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,222 127.2 2.5 GB current
4k 1,289 103.8 2.8 GB view
Batching Results
Batch Size TG tok/s Speedup
127.2 1.00×
198.5 1.56×
228.8 1.80×