← Back to community benchmarks

Qwen3.5-9B

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-10
Performance
1k
tokens
593.0
PP tok/s
92.0
TG tok/s
1727
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 593.0 92.0 6.7 GB current
4k 631.1 88.0 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 92.0 1.00×
2× 119.2 1.30×
4× 136.9 1.49×