← Back to community benchmarks

Qwen3.5-4B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
348.6
PP tok/s
22.7
TG tok/s
11751
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 331.1 23.8 4.8 GB view
4k 348.6 22.7 5.4 GB current
Batching Results
Batch Size TG tok/s Speedup
23.8 1.00×
45.0 1.89×
69.4 2.92×