← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
143.8
PP tok/s
21.5
TG tok/s
7123
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 143.8 21.5 3.9 GB current
4k 128.3 19.6 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
21.5 1.00×
5.5 0.26×
16.0 0.74×