← Back to community benchmarks

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

M4 Pro (20c) · 64 GB · 4bit · 2026-03-10
Performance
16k
tokens
117.2
PP tok/s
13.5
TG tok/s
139806
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.7 0.4 19.4 GB view
4k 123.8 14.9 16.1 GB view
8k 121.3 14.3 16.6 GB view
16k 117.2 13.5 17.5 GB current
32k 110.1 11.5 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
0.4 1.00×
29.7 74.25×
32.0 80.00×
33.3 83.25×