← Back to community benchmarks

Qwen3.5-9B

M2 (8c) · 16 GB · 4bit · 2026-03-12
Performance
1k
tokens
84.2
PP tok/s
18.2
TG tok/s
12166
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M2 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.2 18.2 6.5 GB current
4k 87.1 18.1 6.8 GB view
Batching Results
Batch Size TG tok/s Speedup
18.2 1.00×
20.7 1.14×
21.1 1.16×