← Back to community benchmarks

Qwen3.5-9B

M2 Max (38c) · 32 GB · 4bit · 2026-03-10
Performance
1k
tokens
288.3
PP tok/s
46.1
TG tok/s
3552
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 288.3 46.1 6.7 GB current
4k 259.8 32.9 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
46.1 1.00×
43.2 0.94×
40.8 0.89×