← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-14
Performance
4k
tokens
364.0
PP tok/s
47.8
TG tok/s
11254
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.11
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 364.0 49.8 6.7 GB view
4k 364.0 47.8 7.0 GB current
8k 350.3 43.9 7.1 GB view
16k 341.1 41.6 7.6 GB view
32k 308.2 31.2 8.7 GB view
Batching Results
Batch Size TG tok/s Speedup
49.8 1.00×
74.2 1.49×
76.0 1.53×