← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 4bit · 2026-03-09
Performance
1k
tokens
1,107
PP tok/s
85.6
TG tok/s
925
TTFT (ms)
43.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 15.6
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,107 85.6 43.0 GB current
4k 1,242 79.1 43.2 GB view
Batching Results
Batch Size TG tok/s Speedup
85.6 1.00×
133.1 1.55×
197.5 2.31×
276.0 3.22×