← Back to community benchmarks

Qwen3-Coder-Next-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-05-04
Performance
1k
tokens
1,947
PP tok/s
76.4
TG tok/s
526
TTFT (ms)
80.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,947 76.4 80.2 GB current
195k 845.4 36.7 97.8 GB view