← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
295.9
PP tok/s
31.9
TG tok/s
13842
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 305.1 37.0 3.9 GB view
4k 295.9 31.9 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
37.0 1.00×
62.8 1.70×
57.6 1.56×