← Back to community benchmarks

Qwen3.5-4B-OptiQ

M4 (8c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
254.9
PP tok/s
23.3
TG tok/s
4018
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.7.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 254.9 23.3 4.8 GB current
4k 263.4 22.1 5.4 GB view
Batching Results
Batch Size TG tok/s Speedup
23.3 1.00×
44.8 1.92×
56.8 2.44×
58.6 2.52×