← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-03-14
Performance
16k
tokens
117.0
PP tok/s
6.3
TG tok/s
139994
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.11
macOS macOS 15.7.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 201.0 22.4 15.8 GB view
4k 199.8 17.5 16.1 GB view
8k 178.2 16.6 16.6 GB view
16k 117.0 6.3 17.5 GB current
Batching Results
Batch Size TG tok/s Speedup
22.4 1.00×
19.9 0.89×
23.8 1.06×