← Back to community benchmarks

Qwen3.5-2B

M4 Pro (16c) · 24 GB · unknown · 2026-03-12
Performance
4k
tokens
1,293
PP tok/s
12.6
TG tok/s
3169
TTFT (ms)
7.2
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,028 12.6 7.1 GB view
4k 1,293 12.6 7.2 GB current
8k 1,393 12.3 7.2 GB view
16k 1,352 12.2 7.4 GB view
32k 1,171 9.9 8.4 GB view
Batching Results
Batch Size TG tok/s Speedup
12.6 1.00×
20.4 1.62×
38.0 3.02×