← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-03-12
Performance
1k
tokens
77.3
PP tok/s
10.6
TG tok/s
13250
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.8
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 77.3 10.6 6.5 GB current
4k 67.1 11.9 6.8 GB view
Batching Results
Batch Size TG tok/s Speedup
10.6 1.00×
19.1 1.80×
15.6 1.47×