← Back to community benchmarks

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

M1 Max (24c) · 32 GB · 4bit · 2026-03-12
Performance
16k
tokens
66.3
PP tok/s
10.5
TG tok/s
246967
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 66.6 13.6 15.8 GB view
4k 67.9 12.7 16.1 GB view
8k 67.5 12.2 16.6 GB view
16k 66.3 10.5 17.5 GB current
32k 63.6 8.6 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
13.6 1.00×
16.0 1.18×
17.7 1.30×