← Back to community benchmarks

Qwen3.5-9B

M1 (7c) · 16 GB · 4bit · 2026-04-06
Performance
1k
tokens
64.8
PP tok/s
12.6
TG tok/s
15807
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.3.4
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 64.8 12.6 5.7 GB current
4k 63.5 12.3 6.3 GB view
Batching Results
Batch Size TG tok/s Speedup
12.6 1.00×
14.7 1.17×
15.4 1.22×