← Back to community benchmarks

Qwen3-Coder-Next

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-09
Performance
32k
tokens
734.9
PP tok/s
39.5
TG tok/s
44591
TTFT (ms)
44.7
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 32,768