← Back to community benchmarks

Qwen3-Coder-Next

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10
Performance
1k
tokens
1,245
PP tok/s
61.1
TG tok/s
822
TTFT (ms)
80.1
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,245 61.1 80.1 GB current
4k 1,801 58.6 80.3 GB view
8k 1,884 55.9 80.5 GB view
16k 1,793 50.8 80.9 GB view
32k 1,555 43.2 81.8 GB view
64k 1,190 32.9 83.6 GB view
Batching Results
Batch Size TG tok/s Speedup
61.1 1.00×
103.8 1.70×
170.2 2.79×
247.9 4.06×