← Back to community benchmarks

Qwen3.5-4B

M3 Pro (14c) · 18 GB · 4bit · 2026-03-11
Performance
1k
tokens
479.1
PP tok/s
48.1
TG tok/s
2137
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 18 GB
GPU Cores 14
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 479.1 48.1 4.0 GB current
4k 489.7 42.8 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
48.1 1.00×
91.2 1.90×
92.2 1.92×