← Back to community benchmarks

Qwen3.6-27B-FP8-source-oQ4-mtp

M4 Max (40c) · 128 GB · 4bit · 2026-05-07
Performance
1k
tokens
236.5
PP tok/s
38.6
TG tok/s
4329
TTFT (ms)
16.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 236.5 38.6 16.9 GB current
4k 184.8 27.6 18.4 GB view
8k 179.4 31.9 19.4 GB view
16k 159.6 22.4 20.9 GB view
32k 154.2 22.8 23.9 GB view
64k 139.6 18.9 29.9 GB view
Batching Results
Batch Size TG tok/s Speedup
38.6 1.00×
34.9 0.90×
40.3 1.04×