← Back to community benchmarks

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

M1 Pro (16c) · 32 GB · 4bit · 2026-03-09
Performance
4k
tokens
39.4
PP tok/s
8.3
TG tok/s
104091
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 15.6
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 38.8 8.7 15.8 GB view
4k 39.4 8.3 16.1 GB current
8k 39.0 7.9 16.6 GB view
16k 38.2 6.8 17.5 GB view
Batching Results
Batch Size TG tok/s Speedup
8.7 1.00×
11.8 1.36×
12.2 1.40×