← Back to community benchmarks

Qwen3.5-2B-Polaris-HighIQ-INSTRUCT

M4 Pro (16c) · 24 GB · unknown · 2026-04-18
Performance
8k
tokens
1,737
PP tok/s
59.5
TG tok/s
4717
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,373 62.1 4.2 GB view
4k 1,705 59.2 4.7 GB view
8k 1,737 59.5 4.9 GB current
16k 1,703 57.4 5.2 GB view
32k 1,530 51.6 5.9 GB view
64k 1,275 43.2 7.3 GB view
Batching Results
Batch Size TG tok/s Speedup
62.1 1.00×
51.5 0.83×
100.3 1.62×
188.3 3.03×