← Back to community benchmarks

Qwen3.5-4B

M3 Pro (14c) · 36 GB · 4bit · 2026-04-16
Performance
32k
tokens
402.9
PP tok/s
30.3
TG tok/s
81334
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 447.1 48.8 3.4 GB view
4k 478.6 46.5 4.1 GB view
8k 474.9 43.4 4.5 GB view
16k 451.2 37.7 5.2 GB view
32k 402.9 30.3 6.7 GB current
64k 332.3 17.9 9.7 GB view
128k 236.2 9.6 16.1 GB view