← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 (10c) · 32 GB · 4bit · 2026-05-10
Performance
4k
tokens
62.4
PP tok/s
10.7
TG tok/s
65623
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 62.5 9.8 16.7 GB view
4k 62.4 10.7 18.1 GB current
Batching Results
Batch Size TG tok/s Speedup
9.8 1.00×
12.3 1.26×
14.1 1.44×