← Back to community benchmarks

Qwen3.5-27B

M2 Ultra (76c) · 192 GB · 8bit · 2026-03-09
Performance
4k
tokens
224.2
PP tok/s
19.3
TG tok/s
18273
TTFT (ms)
29.5
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 15.0
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 220.8 20.4 29.1 GB view
4k 224.2 19.3 29.5 GB current
8k 222.6 18.8 29.9 GB view
16k 218.2 17.6 30.8 GB view
32k 203.4 15.2 32.6 GB view
64k 144.2 12.2 36.2 GB view
Batching Results
Batch Size TG tok/s Speedup
20.4 1.00×
36.6 1.79×
50.6 2.48×
61.1 3.00×