← Back to community benchmarks

Qwen3-Coder-Next

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-17
Performance
1k
tokens
1,302
PP tok/s
65.5
TG tok/s
787
TTFT (ms)
80.1
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.6
macOS macOS 26.4
Context 1,024