← Back to community benchmarks

Qwen3-Coder-Next-mxfp4

M1 Max (32c) · 64 GB · 4bit · 2026-03-18
Performance
8k
tokens
437.2
PP tok/s
42.5
TG tok/s
18737
TTFT (ms)
42.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.18
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 391.2 46.7 40.8 GB view
4k 454.5 45.3 41.7 GB view
8k 437.2 42.5 42.1 GB current
16k 414.9 35.2 42.8 GB view
32k 371.8 26.9 44.2 GB view
64k 298.4 18.3 47.0 GB view
Batching Results
Batch Size TG tok/s Speedup
46.7 1.00×
67.5 1.45×
86.4 1.85×
104.8 2.24×