← Back to community benchmarks

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

M4 Max (40c) · 64 GB · 4bit · 2026-05-03
Performance
16k
tokens
217.4
PP tok/s
21.0
TG tok/s
75368
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 236.9 29.1 15.8 GB view
4k 243.9 28.0 17.3 GB view
8k 222.6 27.1 18.3 GB view
16k 217.4 21.0 19.8 GB current
Batching Results
Batch Size TG tok/s Speedup
29.1 1.00×
40.5 1.39×
42.6 1.46×
42.4 1.46×