← Back to community benchmarks

Qwen3.5-27BMTP

M5 Max (40c) · 128 GB · 8bit · 2026-05-15
Performance
16k
tokens
699.4
PP tok/s
26.2
TG tok/s
23427
TTFT (ms)
32.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 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 721.5 29.2 28.8 GB view
4k 789.2 28.2 30.3 GB view
8k 762.8 26.5 31.3 GB view
16k 699.4 26.2 32.8 GB current
32k 630.2 24.4 35.8 GB view
Batching Results
Batch Size TG tok/s Speedup
29.2 1.00×
34.8 1.19×
47.7 1.63×