← Back to community benchmarks

Qwen3.5-27B

M2 Max (38c) · 32 GB · 4bit · 2026-03-12
Performance
1k
tokens
115.2
PP tok/s
20.8
TG tok/s
8886
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 20.8 1.00×
2× 27.6 1.33×
4× 30.0 1.44×
8× 20.3 0.98×