← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
319.9
PP tok/s
22.6
TG tok/s
12803
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 300.4 | 23.0 | 28.3 GB | view |
| 4k | 319.9 | 22.6 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.0 | 1.00× |
| 2× | 39.3 | 1.71× |
| 4× | 78.4 | 3.41× |