← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-11
Performance
1k
tokens
144.7
PP tok/s
22.2
TG tok/s
7075
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 144.7 22.2 3.9 GB current
4k 143.9 20.7 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
22.2 1.00×
33.2 1.50×
34.1 1.54×