← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
1,648
PP tok/s
60.9
TG tok/s
621
TTFT (ms)
80.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024