← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
74.0
PP tok/s
11.4
TG tok/s
55323
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 77.1 11.7 6.5 GB view
4k 74.0 11.4 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
11.7 1.00×
18.3 1.56×
19.1 1.63×