← Back to community benchmarks

Qwen3.5-9B

M4 Pro (20c) · 48 GB · 4bit · 2026-03-11
Performance
8k
tokens
413.7
PP tok/s
41.8
TG tok/s
19801
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 419.9 47.7 6.7 GB view
4k 421.1 45.0 7.0 GB view
8k 413.7 41.8 7.1 GB current
Batching Results
Batch Size TG tok/s Speedup
47.7 1.00×
89.6 1.88×
92.1 1.93×