← Back to community benchmarks

Qwen3.5-27B

M3 Max (40c) · 128 GB · 4bit · 2026-03-11
Performance
4k
tokens
217.6
PP tok/s
20.9
TG tok/s
18825
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 15.6.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 217.1 22.0 16.6 GB view
4k 217.6 20.9 17.0 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 22.0 1.00×
2× 41.7 1.90×
4× 48.5 2.20×