← Back to community benchmarks

Qwen3-Next-80B-A3B-Instruct

M3 Max (40c) · 128 GB · 6bit · 2026-03-10
Performance
1k
tokens
830.8
PP tok/s
60.1
TG tok/s
1233
TTFT (ms)
61.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 830.8 60.1 61.6 GB current
4k 1,050 57.4 61.7 GB view
Batching Results
Batch Size TG tok/s Speedup
60.1 1.00×
94.3 1.57×
119.1 1.98×