← Back to community benchmarks

Qwen3.5-9B-oQ4e-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-07-14
Performance
64k
tokens
660.9
PP tok/s
57.8
TG tok/s
99156
TTFT (ms)
12.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 65,536