← Back to community benchmarks

Qwen3.5-4B-Uncensored

M5 (10c) · 24 GB · 4bit · 2026-04-15
Performance
16k
tokens
1,004
PP tok/s
38.3
TG tok/s
16314
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.5
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,130 45.5 3.9 GB view
8k 1,100 43.1 4.3 GB view
16k 1,004 38.3 5.0 GB current
32k 805.6 30.6 6.5 GB view