← Back to community benchmarks

Qwen3.5-4B-unsloth

M1 (8c) · 16 GB · 3bit · 2026-04-25
Performance
32k
tokens
191.5
PP tok/s
12.7
TG tok/s
171107
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 223.7 19.0 3.8 GB view
32k 191.5 12.7 7.0 GB current
64k 146.5 9.4 10.0 GB view