← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-12
Performance
1k
tokens
309.8
PP tok/s
38.4
TG tok/s
3306
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 38.4 1.00×
2× 68.1 1.77×
4× 71.9 1.87×
8× 71.5 1.86×