← Back to community benchmarks
Qwen3.6-27BoQ8
Performance
16k
tokens
408.6
PP tok/s
20.4
TG tok/s
40102
TTFT (ms)
32.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.8
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 387.0 | 21.5 | 28.3 GB | view |
| 4k | 419.6 | 21.3 | 29.8 GB | view |
| 8k | 419.3 | 20.9 | 30.8 GB | view |
| 16k | 408.6 | 20.4 | 32.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.5 | 1.00× |
| 2× | 38.5 | 1.79× |
| 4× | 57.5 | 2.67× |