← Back to community benchmarks

Qwen3-Coder-Next

M3 Ultra (60c) · 256 GB · 4bit · 2026-03-10
Performance
1k
tokens
1,318
PP tok/s
73.0
TG tok/s
777
TTFT (ms)
43.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,318 73.0 43.0 GB current
4k 1,556 70.4 43.2 GB view
8k 1,553 67.5 43.4 GB view
16k 1,460 59.4 43.9 GB view
32k 1,279 49.8 44.7 GB view
64k 1,002 37.0 46.5 GB view
Batching Results
Batch Size TG tok/s Speedup
73.0 1.00×
123.5 1.69×
194.6 2.67×
285.0 3.90×