← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 48 GB · 4bit · 2026-05-15
User commentSpec prefil=true, Native MTP=true
Performance
1k
tokens
120.2
PP tok/s
21.3
TG tok/s
8522
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 120.2 21.3 16.7 GB current
4k 120.3 22.0 18.2 GB view
Batching Results
Batch Size TG tok/s Speedup
21.3 1.00×
25.4 1.19×
28.0 1.31×