← Back to community benchmarks

Qwen3-Next-80B-A3B-Instruct6bit-gs64

M2 Max (38c) · 96 GB · 6bit · 2026-03-11
Performance
1k
tokens
470.5
PP tok/s
53.2
TG tok/s
2177
TTFT (ms)
61.6
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.2.7
macOS macOS 15.7.3
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
53.2 1.00×
78.2 1.47×
102.2 1.92×
122.5 2.30×