← Back to community benchmarks

Qwen3.5-27BMTP

M5 Max (40c) · 64 GB · 4bit · 2026-05-18
Performance
16k
tokens
693.8
PP tok/s
37.8
TG tok/s
23615
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 581.4 46.5 16.1 GB view
4k 821.0 45.9 17.6 GB view
8k 725.0 41.3 18.6 GB view
16k 693.8 37.8 20.1 GB current
Batching Results
Batch Size TG tok/s Speedup
46.5 1.00×
52.8 1.14×
65.4 1.41×