← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
227.3
PP tok/s
29.3
TG tok/s
18023
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
128 GB
GPU Cores
76
Software
oMLX
v0.3.9.dev1
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 212.7 | 30.9 | 28.8 GB | view |
| 4k | 227.3 | 29.3 | 30.3 GB | current |
| 8k | 227.3 | 28.9 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.9 | 1.00× |
| 2× | 38.0 | 1.23× |
| 4× | 51.8 | 1.68× |