← Back to community benchmarks
Qwen3-Coder-Next
Performance
16k
tokens
506.1
PP tok/s
51.3
TG tok/s
32375
TTFT (ms)
44.1
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 506.1 | 51.3 | 44.1 GB | current |
| 64k | 307.4 | 33.9 | 45.4 GB | view |