← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-29
Performance
4k
tokens
78.5
PP tok/s
12.4
TG tok/s
52155
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.8rc1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 77.2 12.5 5.7 GB view
4k 78.5 12.4 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
12.5 1.00×
18.7 1.50×
15.2 1.22×