← Back to community benchmarks

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

M4 Max (40c) · 64 GB · 4bit · 2026-06-17
Performance
32k
tokens
217.8
PP tok/s
25.4
TG tok/s
150479
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.6
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 242.0 30.2 15.8 GB view
4k 245.7 28.9 17.3 GB view
8k 224.8 28.3 18.3 GB view
16k 231.3 27.0 19.8 GB view
32k 217.8 25.4 22.8 GB current
Batching Results
Batch Size TG tok/s Speedup
30.2 1.00×
51.7 1.71×
59.2 1.96×
63.8 2.11×