← Back to community benchmarks

Qwen3.5-9B

M1 Max (32c) · 64 GB · 4bit · 2026-03-10
Performance
64k
tokens
264.1
PP tok/s
22.9
TG tok/s
248122
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
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 314.3 56.6 6.7 GB view
4k 319.5 54.1 7.0 GB view
8k 316.4 49.6 7.1 GB view
16k 309.8 43.6 7.6 GB view
32k 296.6 33.0 8.7 GB view
64k 264.1 22.9 10.8 GB current
Batching Results
Batch Size TG tok/s Speedup
56.6 1.00×
61.3 1.08×
64.3 1.14×