← Back to community benchmarks

Qwen3.5-4B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
338.3
PP tok/s
19.9
TG tok/s
12107
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 323.2 21.3 4.8 GB view
4k 338.3 19.9 5.4 GB current
Batching Results
Batch Size TG tok/s Speedup
21.3 1.00×
40.5 1.90×
66.4 3.12×