← Back to community benchmarks

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

M4 Pro (20c) · 48 GB · 4bit · 2026-03-11
Performance
16k
tokens
121.2
PP tok/s
12.7
TG tok/s
135126
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 15.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 122.8 15.5 15.8 GB view
4k 126.0 15.0 16.1 GB view
8k 124.7 14.1 16.6 GB view
16k 121.2 12.7 17.5 GB current
32k 113.1 7.6 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
15.5 1.00×
28.5 1.84×
32.4 2.09×