← Back to community benchmarks

Qwen3.5-2B

M4 Pro (20c) · 48 GB · 6bit · 2026-03-09
Performance
1k
tokens
1,768
PP tok/s
113.3
TG tok/s
579
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,768 113.3 3.1 GB current
4k 1,797 109.1 3.2 GB view
Batching Results
Batch Size TG tok/s Speedup
113.3 1.00×
187.3 1.65×
209.7 1.85×