← Back to community benchmarks

Qwen3.5-9B

M2 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
85.9
PP tok/s
18.7
TG tok/s
11915
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M2 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 85.9 18.7 6.5 GB current
4k 84.6 17.2 6.8 GB view
Batching Results
Batch Size TG tok/s Speedup
18.7 1.00×
19.7 1.05×
13.5 0.72×