← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
225.9
PP tok/s
24.6
TG tok/s
72533
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 257.7 | 27.6 | 16.4 GB | view |
| 4k | 246.1 | 26.9 | 17.9 GB | view |
| 16k | 225.9 | 24.6 | 20.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.6 | 1.00× |
| 2× | 49.2 | 1.78× |
| 4× | 55.7 | 2.02× |