← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-06
Performance
1k
tokens
75.6
PP tok/s
12.4
TG tok/s
13540
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.0
macOS macOS 26.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 75.6 12.4 5.7 GB current
4k 75.5 7.9 6.4 GB view
Batching Results
Batch Size TG tok/s Speedup
12.4 1.00×
13.3 1.07×
18.3 1.48×