← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
317.1
PP tok/s
41.5
TG tok/s
25831
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 302.2 | 42.6 | 16.8 GB | view |
| 4k | 318.4 | 43.2 | 18.2 GB | view |
| 8k | 317.1 | 41.5 | 19.2 GB | current |
| 16k | 308.7 | 38.8 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.6 | 1.00× |
| 2× | 45.7 | 1.07× |
| 4× | 62.5 | 1.47× |