← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
228.8
PP tok/s
25.4
TG tok/s
35810
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 240.9 | 26.9 | 16.4 GB | view |
| 4k | 239.1 | 26.3 | 17.9 GB | view |
| 8k | 228.8 | 25.4 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.9 | 1.00× |
| 2× | 47.2 | 1.75× |
| 4× | 52.8 | 1.96× |