← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
247.8
PP tok/s
26.4
TG tok/s
33055
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 241.8 | 28.2 | 16.4 GB | view |
| 4k | 249.3 | 27.1 | 17.9 GB | view |
| 8k | 247.8 | 26.4 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.2 | 1.00× |
| 2× | 49.4 | 1.75× |
| 4× | 55.5 | 1.97× |
| 8× | 58.6 | 2.08× |