← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
16k
tokens
399.7
PP tok/s
27.6
TG tok/s
40991
TTFT (ms)
32.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 381.1 | 30.4 | 28.8 GB | view |
| 4k | 417.5 | 31.0 | 30.3 GB | view |
| 8k | 413.1 | 30.1 | 31.3 GB | view |
| 16k | 399.7 | 27.6 | 32.8 GB | current |
| 32k | 381.6 | 26.7 | 35.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.4 | 1.00× |
| 2× | 37.9 | 1.25× |
| 4× | 50.9 | 1.67× |
| 8× | 68.3 | 2.25× |