← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
302.2
PP tok/s
36.7
TG tok/s
3389
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 302.2 36.7 3.9 GB current
4k 301.0 34.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
36.7 1.00×
64.4 1.75×
71.3 1.94×
72.5 1.98×