← Back to community benchmarks
Qwen3-Coder-Next-oQ8
Performance
1k
tokens
1,745
PP tok/s
59.1
TG tok/s
587
TTFT (ms)
80.2
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