← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
301.4
PP tok/s
19.2
TG tok/s
13590
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 310.0 37.0 3.9 GB view
4k 301.4 19.2 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
37.0 1.00×
66.6 1.80×
67.7 1.83×