← Back to community benchmarks

Qwen3.5-9B-oQ8

M2 Pro (16c) · 16 GB · 8bit · 2026-04-26
Performance
4k
tokens
300.5
PP tok/s
20.6
TG tok/s
13629
TTFT (ms)
10.6
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.3.7rc2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 281.5 21.2 9.9 GB view
4k 300.5 20.6 10.6 GB current
Batching Results
Batch Size TG tok/s Speedup
21.2 1.00×
38.8 1.83×
49.5 2.33×