← Back to community benchmarks

Qwen3.5-9B

M1 Max (32c) · 64 GB · 4bit · 2026-03-10
Performance
1k
tokens
309.3
PP tok/s
55.6
TG tok/s
3311
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 309.3 55.6 6.7 GB current
4k 318.1 53.7 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
55.6 1.00×
67.0 1.21×
71.7 1.29×