← Back to community benchmarks

Qwen3.5-9B

M1 Max (24c) · 64 GB · 4bit · 2026-04-06
Performance
128k
tokens
165.6
PP tok/s
12.1
TG tok/s
791459
TTFT (ms)
18.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.2
macOS macOS 26.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
128k 165.6 12.1 18.7 GB current
195k 139.5 4.7 25.3 GB view