← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
32k
tokens
198.8
PP tok/s
17.9
TG tok/s
164794
TTFT (ms)
29.9
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 199.2 | 22.8 | 23.0 GB | view |
| 4k | 213.5 | 21.3 | 24.4 GB | view |
| 8k | 215.1 | 19.9 | 25.4 GB | view |
| 16k | 210.9 | 18.4 | 26.9 GB | view |
| 32k | 198.8 | 17.9 | 29.9 GB | current |
| 64k | 163.7 | 14.9 | 36.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.8 | 1.00× |
| 2× | 27.1 | 1.19× |
| 4× | 30.6 | 1.34× |