← Back to community benchmarks

Qwen3.5-9B

M2 Ultra (76c) · 192 GB · 4bit · 2026-03-09
Performance
64k
tokens
665.7
PP tok/s
44.3
TG tok/s
98447
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 727.6 96.7 6.7 GB view
4k 789.6 93.2 7.0 GB view
8k 792.6 87.6 7.1 GB view
16k 774.4 76.6 7.6 GB view
32k 738.1 61.9 8.7 GB view
64k 665.7 44.3 10.8 GB current
Batching Results
Batch Size TG tok/s Speedup
96.7 1.00×
135.8 1.40×
161.6 1.67×
182.6 1.89×