← Back to community benchmarks

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

M4 (10c) · 32 GB · 4bit · 2026-03-11
Performance
16k
tokens
56.8
PP tok/s
6.0
TG tok/s
288570
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 62.5 6.0 15.7 GB view
4k 63.2 6.7 16.1 GB view
8k 61.6 6.4 16.5 GB view
16k 56.8 6.0 17.4 GB current
Batching Results
Batch Size TG tok/s Speedup
6.0 1.00×
13.5 2.25×
16.3 2.72×