← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-15
Performance
4k
tokens
152.2
PP tok/s
22.4
TG tok/s
26903
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 147.5 23.4 16.7 GB view
4k 152.2 22.4 18.1 GB current
8k 150.9 21.9 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
23.4 1.00×
27.3 1.17×
29.9 1.28×