← Back to community benchmarks

Qwen3.5-4B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-16
Performance
16k
tokens
353.5
PP tok/s
26.4
TG tok/s
46345
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.13
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 375.3 32.6 3.8 GB view
4k 394.7 31.3 4.1 GB view
8k 385.7 29.6 4.3 GB view
16k 353.5 26.4 4.8 GB current
32k 310.2 20.6 5.8 GB view