← Back to community benchmarks

Qwen3.5-2B

M5 Pro (16c) · 48 GB · 4bit · 2026-07-13
Performance
64k
tokens
1,864
PP tok/s
113.3
TG tok/s
35157
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 3,475 154.1 2.5 GB view
64k 1,864 113.3 3.1 GB current