← Back to community benchmarks

Qwen3.5-9B-OptiQ

M5 (10c) · 32 GB · 4bit · 2026-04-25
Performance
4k
tokens
776.0
PP tok/s
24.4
TG tok/s
5279
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 699.5 25.1 6.7 GB view
4k 776.0 24.4 7.3 GB current
Batching Results
Batch Size TG tok/s Speedup
25.1 1.00×
50.8 2.02×
70.0 2.79×