← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
255.5
PP tok/s
37.4
TG tok/s
4008
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 255.5 | 37.4 | 16.7 GB | current |
| 4k | 224.3 | 38.2 | 18.2 GB | view |