← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-11
Performance
1k
tokens
282.0
PP tok/s
34.2
TG tok/s
3631
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 282.0 34.2 3.9 GB current
4k 278.0 30.7 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
34.2 1.00×
60.5 1.77×
65.8 1.92×