← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-14
Performance
1k
tokens
143.1
PP tok/s
21.0
TG tok/s
7155
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.11
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 143.1 21.0 3.9 GB current
4k 142.2 19.5 4.2 GB view