← Back to community benchmarks

Qwen3.5-27B

M3 Max (40c) · 48 GB · 4bit · 2026-03-12
Performance
8k
tokens
186.9
PP tok/s
17.5
TG tok/s
43833
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 172.1 17.9 16.6 GB view
4k 188.6 19.1 17.0 GB view
8k 186.9 17.5 17.4 GB current
16k 176.5 15.5 18.3 GB view
Batching Results
Batch Size TG tok/s Speedup
17.9 1.00×
28.4 1.59×
35.6 1.99×