← Back to community benchmarks

Qwen3.5-4B

M1 Pro (16c) · 32 GB · 8bit · 2026-03-10
Performance
16k
tokens
274.2
PP tok/s
26.7
TG tok/s
59755
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 15.7.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 271.2 33.5 5.9 GB view
4k 255.6 30.0 6.1 GB view
8k 274.1 31.0 6.5 GB view
16k 274.2 26.7 7.3 GB current
32k 249.9 20.2 7.9 GB view