← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 4bit · 2026-07-20
Performance
1k
tokens
1,227
PP tok/s
64.5
TG tok/s
835
TTFT (ms)
43.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,227 64.5 43.1 GB current
4k 1,354 64.8 43.8 GB view
64k 746.4 52.1 45.2 GB view
Batching Results
Batch Size TG tok/s Speedup
64.5 1.00×
118.2 1.83×
183.4 2.84×
270.7 4.20×