← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 8bit · 2026-03-09
Performance
4k
tokens
1,192
PP tok/s
63.1
TG tok/s
3437
TTFT (ms)
80.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 944.3 64.0 80.1 GB view
4k 1,192 63.1 80.3 GB current
Batching Results
Batch Size TG tok/s Speedup
64.0 1.00×
111.7 1.75×
155.5 2.43×