← Back to community benchmarks

Qwen3.5-9B

M3 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
151.8
PP tok/s
18.4
TG tok/s
26975
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M3 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 151.6 19.3 6.5 GB view
4k 151.8 18.4 7.3 GB current
Batching Results
Batch Size TG tok/s Speedup
19.3 1.00×
35.7 1.85×
36.0 1.87×