← Back to community benchmarks

Llama-3.3-70B

M4 Max (40c) · 64 GB · 4bit · 2026-03-12
Performance
1k
tokens
87.4
PP tok/s
10.7
TG tok/s
11721
TTFT (ms)
37.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 87.4 10.7 37.8 GB current
4k 69.4 8.5 39.0 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 10.7 1.00×
2× 6.9 0.64×