← Back to community benchmarks

Qwen3.5-9B

M3 Max (30c) · 36 GB · 4bit · 2026-04-24
Performance
1k
tokens
523.7
PP tok/s
54.1
TG tok/s
1955
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.7
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 523.7 54.1 5.8 GB current
8k 563.5 49.5 6.9 GB view
16k 499.6 45.4 7.6 GB view
32k 467.7 37.0 9.1 GB view
64k 310.3 14.6 12.2 GB view
Batching Results
Batch Size TG tok/s Speedup
54.1 1.00×
38.3 0.71×
55.5 1.03×