← Back to community benchmarks

Qwen3.5-4B

M3 (10c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
273.9
PP tok/s
21.3
TG tok/s
14954
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 320.6 24.0 3.9 GB view
4k 273.9 21.3 4.2 GB current
8k 207.1 18.4 4.6 GB view
Batching Results
Batch Size TG tok/s Speedup
24.0 1.00×
43.0 1.79×
49.6 2.07×
47.2 1.97×