← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
32k
tokens
227.0
PP tok/s
17.1
TG tok/s
144337
TTFT (ms)
35.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.0
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 240.4 | 24.3 | 32.1 GB | view |
| 32k | 227.0 | 17.1 | 35.8 GB | current |