← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi

M3 Max (30c) · 36 GB · 6bit · 2026-03-11
Performance
1k
tokens
155.8
PP tok/s
13.9
TG tok/s
6574
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.2.8b1
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 155.8 13.9 19.9 GB current
4k 153.3 13.6 20.3 GB view
Batching Results
Batch Size TG tok/s Speedup
13.9 1.00×
24.4 1.76×
14.3 1.03×