← Back to community benchmarks

Qwen3.5-27B

M3 Max (40c) · 128 GB · 8bit · 2026-03-14
Performance
195k
tokens
97.2
PP tok/s
2.4
TG tok/s
2058410
TTFT (ms)
86.3
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.11
macOS macOS 15.7.4
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 211.6 12.9 29.1 GB view
4k 210.6 12.6 29.5 GB view
8k 187.4 11.8 29.9 GB view
16k 189.9 10.2 30.8 GB view
32k 173.0 7.9 32.6 GB view
64k 149.2 3.8 68.7 GB view
128k 118.0 4.5 78.6 GB view
195k 97.2 2.4 86.3 GB current
Batching Results
Batch Size TG tok/s Speedup
12.9 1.00×
22.9 1.78×
29.3 2.27×
29.8 2.31×