← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 8bit · 2026-03-11
Performance
1k
tokens
75.2
PP tok/s
6.7
TG tok/s
13608
TTFT (ms)
10.6
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 75.2 6.7 10.6 GB current
4k 75.9 6.5 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
6.7 1.00×
13.1 1.96×
21.3 3.18×