← Back to community benchmarks

Qwen3.5-9B-MXF8

M5 (10c) · 24 GB · 8bit · 2026-04-28
Performance
8k
tokens
732.6
PP tok/s
14.6
TG tok/s
11182
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 540.9 100.4 11.9 GB view
4k 403.2 14.9 10.6 GB view
8k 732.6 14.6 10.9 GB current