← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Distilled

M2 Pro (16c) · 32 GB · 4bit · 2026-03-11
Performance
4k
tokens
46.8
PP tok/s
10.5
TG tok/s
87594
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.8
macOS macOS 26.0.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 43.0 5.7 15.8 GB view
4k 46.8 10.5 16.4 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 5.7 1.00×
2× 13.0 2.28×