← Back to community benchmarks

Qwen3.5-27B

M2 Max (38c) · 64 GB · 4bit · 2026-03-12
Performance
1k
tokens
105.7
PP tok/s
13.9
TG tok/s
9692
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 105.7 13.9 16.6 GB current
4k 94.9 12.7 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 13.9 1.00×
2× 16.0 1.15×
4× 20.3 1.46×