← Back to community benchmarks

Qwen3.5-9B

M2 Ultra (60c) · 128 GB · 4bit · 2026-03-10
Performance
1k
tokens
589.6
PP tok/s
90.6
TG tok/s
1737
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 128 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 589.6 90.6 6.7 GB current
4k 621.7 86.8 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
90.6 1.00×
118.1 1.30×
136.8 1.51×
148.1 1.63×