← Back to community benchmarks

Qwen3-Coder-Next

M3 Ultra (60c) · 256 GB · 8bit · 2026-03-08
Performance
8k
tokens
1,521
PP tok/s
56.5
TG tok/s
5386
TTFT (ms)
80.5
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,236 63.9 80.1 GB view
4k 1,509 61.9 80.3 GB view
8k 1,521 56.5 80.5 GB current
16k 1,434 52.0 80.9 GB view
32k 1,262 45.8 81.8 GB view
64k 994.8 34.7 83.6 GB view
Batching Results
Batch Size TG tok/s Speedup
63.9 1.00×
106.5 1.67×
166.3 2.60×
239.1 3.74×