← Back to community benchmarks

Qwen3.5-4B

M5 (8c) · 16 GB · 4bit · 2026-04-18
Performance
4k
tokens
994.2
PP tok/s
46.3
TG tok/s
4120
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M5 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 902.3 48.1 3.3 GB view
4k 994.2 46.3 3.9 GB current
Batching Results
Batch Size TG tok/s Speedup
48.1 1.00×
85.9 1.79×