← Back to community benchmarks
Qwen3-Coder-Next-abliterated-mxfp4-gs32
Performance
64k
tokens
820.2
PP tok/s
32.7
TG tok/s
79898
TTFT (ms)
44.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
65,536