← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
142.9
PP tok/s
21.3
TG tok/s
7164
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 142.9 21.3 3.9 GB current
4k 140.4 20.1 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
21.3 1.00×
32.4 1.52×
34.0 1.60×
27.8 1.31×