← Back to community benchmarks

Qwen3-Coder-Next

M5 Pro (20c) · 64 GB · 4bit · 2026-04-26
Performance
32k
tokens
1,387
PP tok/s
47.7
TG tok/s
23623
TTFT (ms)
46.4
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 378.2 71.5 44.0 GB view
8k 1,716 66.8 44.3 GB view
16k 1,623 61.0 45.0 GB view
32k 1,387 47.7 46.4 GB current
64k 997.2 34.8 49.1 GB view