← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-03-16
Performance
195k
tokens
60.6
PP tok/s
2.4
TG tok/s
3302171
TTFT (ms)
40.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.13
macOS macOS 26.4
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 204.5 22.3 15.8 GB view
4k 193.8 21.0 16.1 GB view
8k 181.6 19.0 16.6 GB view
16k 154.7 9.6 17.5 GB view
32k 102.5 9.6 19.2 GB view
64k 104.3 5.2 22.8 GB view
128k 82.2 3.6 33.0 GB view
195k 60.6 2.4 40.6 GB current
Batching Results
Batch Size TG tok/s Speedup
22.3 1.00×
16.7 0.75×
21.9 0.98×