← Back to community benchmarks

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

M2 Max (38c) · 96 GB · 6bit · 2026-03-11

Performance

4k

tokens

532.5

PP tok/s

50.4

TG tok/s

7692

TTFT (ms)

61.7

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 4,096