← Back to community benchmarks

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

M1 Max (32c) · 32 GB · 4bit · 2026-03-10
Performance
8k
tokens
77.0
PP tok/s
13.4
TG tok/s
106426
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.1 15.1 15.8 GB view
4k 76.8 13.6 16.1 GB view
8k 77.0 13.4 16.6 GB current
16k 75.8 11.8 17.5 GB view
32k 71.7 9.2 19.2 GB view