← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Quality
Performance
8k
tokens
177.6
PP tok/s
18.1
TG tok/s
46117
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 169.4 | 19.3 | 28.3 GB | view |
| 4k | 177.2 | 18.6 | 29.8 GB | view |
| 8k | 177.6 | 18.1 | 30.8 GB | current |
| 16k | 174.9 | 17.4 | 32.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 33.5 | 1.74× |
| 4× | 40.6 | 2.10× |