← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-03-14
Performance
4k
tokens
168.7
PP tok/s
19.9
TG tok/s
24280
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.11
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 168.6 19.8 6.5 GB view
4k 168.7 19.9 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
19.8 1.00×
37.6 1.90×
38.2 1.93×
38.5 1.94×