← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
578.5
PP tok/s
23.2
TG tok/s
56646
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 795.6 | 31.8 | 16.4 GB | view |
| 4k | 842.6 | 31.2 | 17.9 GB | view |
| 8k | 720.6 | 30.5 | 18.9 GB | view |
| 16k | 657.9 | 28.5 | 20.4 GB | view |
| 32k | 578.5 | 23.2 | 23.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.8 | 1.00× |
| 2× | 41.2 | 1.30× |
| 4× | 49.2 | 1.55× |