← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-04-16
Performance
1k
tokens
139.0
PP tok/s
22.4
TG tok/s
7369
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 139.0 22.4 3.3 GB current
4k 139.9 20.8 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
22.4 1.00×
32.4 1.45×
33.1 1.48×