← Back to community benchmarks

Qwen3-Next-80B-A3B-Instruct

M1 Max (32c) · 64 GB · 4bit · 2026-03-11
Performance
8k
tokens
431.4
PP tok/s
37.1
TG tok/s
18989
TTFT (ms)
43.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.7
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 366.8 44.0 43.0 GB view
4k 430.7 43.4 43.2 GB view
8k 431.4 37.1 43.4 GB current
Batching Results
Batch Size TG tok/s Speedup
44.0 1.00×
64.2 1.46×
85.4 1.94×