← Back to community benchmarks

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

M3 (10c) · 24 GB · 4bit · 2026-04-17
Performance
1k
tokens
52.7
PP tok/s
6.1
TG tok/s
19432
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 52.7 6.1 15.8 GB current
4k 47.1 5.4 17.2 GB view
Batching Results
Batch Size TG tok/s Speedup
6.1 1.00×
5.7 0.93×
8.4 1.38×