← Back to community benchmarks

Qwen3.5-9B

M2 (8c) · 16 GB · 4bit · 2026-04-15
Performance
4k
tokens
87.3
PP tok/s
18.1
TG tok/s
46921
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M2 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 86.3 18.8 5.7 GB view
4k 87.3 18.1 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
18.8 1.00×
21.1 1.12×
21.4 1.14×