← Back to community benchmarks

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

M3 Ultra (60c) · 96 GB · 4bit · 2026-03-09
Performance
1k
tokens
303.7
PP tok/s
38.3
TG tok/s
3372
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 303.7 38.3 15.8 GB current
4k 319.0 36.6 16.1 GB view
Batching Results
Batch Size TG tok/s Speedup
38.3 1.00×
62.8 1.64×
71.9 1.88×