← Back to community benchmarks
Qwen3.6-27B-UD
Performance
8k
tokens
420.0
PP tok/s
23.1
TG tok/s
19503
TTFT (ms)
27.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 374.9 | 24.5 | 25.2 GB | view |
| 4k | 418.9 | 23.8 | 26.6 GB | view |
| 8k | 420.0 | 23.1 | 27.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.5 | 1.00× |
| 2× | 30.4 | 1.24× |
| 4× | 50.7 | 2.07× |
| 8× | 75.9 | 3.10× |