← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-11
Performance
1k
tokens
138.3
PP tok/s
19.6
TG tok/s
7404
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 138.3 19.6 3.9 GB current
4k 137.3 18.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
19.6 1.00×
30.9 1.58×
32.7 1.67×