← Back to community benchmarks

Qwen3.5-9B

M5 (8c) · 16 GB · 4bit · 2026-04-18
Performance
4k
tokens
584.4
PP tok/s
24.3
TG tok/s
7009
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M5 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.22
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 609.3 24.9 6.5 GB view
4k 584.4 24.3 7.3 GB current
Batching Results
Batch Size TG tok/s Speedup
24.9 1.00×
43.9 1.76×
42.6 1.71×