← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
249.4
PP tok/s
38.6
TG tok/s
16425
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 241.2 | 39.8 | 16.8 GB | view |
| 4k | 249.4 | 38.6 | 18.2 GB | current |
| 8k | 247.3 | 34.9 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.8 | 1.00× |
| 2× | 48.2 | 1.21× |
| 4× | 55.1 | 1.38× |