← Back to community benchmarks

Qwen3-Coder-Next-oQ8e

M4 Max (40c) · 128 GB · 8bit · 2026-07-13
Performance
128k
tokens
252.2
PP tok/s
23.6
TG tok/s
519689
TTFT (ms)
84.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 432.5 37.6 80.2 GB view
4k 583.7 37.9 80.9 GB view
8k 562.5 36.1 81.2 GB view
16k 599.2 52.2 81.4 GB view
32k 534.9 36.9 81.9 GB view
64k 446.7 32.2 82.7 GB view
128k 252.2 23.6 84.0 GB current
195k 188.9 20.6 85.8 GB view
Batching Results
Batch Size TG tok/s Speedup
37.6 1.00×
69.1 1.84×
100.4 2.67×
126.8 3.37×