← Back to community benchmarks

Qwen3.5-4B

M4 (10c) · 16 GB · 4bit · 2026-03-11
Performance
4k
tokens
403.5
PP tok/s
36.1
TG tok/s
10152
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 403.5 36.1 4.2 GB current
8k 390.8 33.1 4.6 GB view
32k 323.6 22.1 5.9 GB view
64k 251.1 14.2 8.0 GB view