← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 8bit · 2026-04-12
Performance
8k
tokens
1,309
PP tok/s
63.0
TG tok/s
6259
TTFT (ms)
81.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,049 35.3 82.8 GB view
4k 1,321 65.6 81.0 GB view
8k 1,309 63.0 81.4 GB current
Batching Results
Batch Size TG tok/s Speedup
35.3 1.00×
105.9 3.00×