← Back to community benchmarks

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

M4 Pro (20c) · 48 GB · 4bit · 2026-03-09
Performance
4k
tokens
124.8
PP tok/s
15.0
TG tok/s
32808
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.5 15.6 15.8 GB view
4k 124.8 15.0 16.1 GB current
Batching Results
Batch Size TG tok/s Speedup
15.6 1.00×
30.7 1.97×
33.9 2.17×