← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-03-10
Performance
1k
tokens
138.9
PP tok/s
13.1
TG tok/s
7373
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 138.9 13.1 15.8 GB current
4k 141.5 11.6 16.1 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 13.1 1.00×
2× 19.3 1.47×
4× 24.2 1.85×
8× 28.5 2.18×