← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 6bit · 2026-03-11
Performance
32k
tokens
132.0
PP tok/s
8.1
TG tok/s
248221
TTFT (ms)
25.5
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 200.1 16.4 22.0 GB view
4k 190.0 15.8 22.4 GB view
8k 176.6 10.6 22.8 GB view
16k 131.1 7.9 23.7 GB view
32k 132.0 8.1 25.5 GB current
Batching Results
Batch Size TG tok/s Speedup
16.4 1.00×
15.6 0.95×
18.2 1.11×
20.7 1.26×