← Back to community benchmarks

Qwen3.5-2B-Polaris-HighIQ-INSTRUCT-oQ6

M4 Pro (16c) · 24 GB · 6bit · 2026-04-15
Performance
4k
tokens
1,458
PP tok/s
114.3
TG tok/s
2810
TTFT (ms)
2.8
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,231 123.3 2.5 GB view
4k 1,458 114.3 2.8 GB current
Batching Results
Batch Size TG tok/s Speedup
123.3 1.00×
169.2 1.37×
192.7 1.56×