← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-03-11
Performance
16k
tokens
208.8
PP tok/s
17.8
TG tok/s
78471
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 223.0 21.2 6.5 GB view
4k 221.0 20.2 7.3 GB view
8k 217.6 19.9 7.7 GB view
16k 208.8 17.8 8.4 GB current
Batching Results
Batch Size TG tok/s Speedup
21.2 1.00×
39.6 1.87×
51.7 2.44×