← Back to community benchmarks

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

M1 Ultra (64c) · 128 GB · 4bit · 2026-03-12
Performance
1k
tokens
164.5
PP tok/s
28.8
TG tok/s
6226
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 164.5 28.8 15.8 GB current
4k 172.7 27.0 16.1 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 28.8 1.00×
2× 36.5 1.27×
4× 42.0 1.46×