← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-03-11
Performance
4k
tokens
167.0
PP tok/s
20.4
TG tok/s
24526
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 165.2 21.0 6.5 GB view
4k 167.0 20.4 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
21.0 1.00×
39.4 1.88×