← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
78.9
PP tok/s
13.0
TG tok/s
12972
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 78.9 13.0 6.5 GB current
4k 79.3 12.4 6.8 GB view
Batching Results
Batch Size TG tok/s Speedup
13.0 1.00×
19.0 1.46×
19.5 1.50×