← Back to community benchmarks
Qwen3.6-27B-Architect-Polaris-Fable-qx64-hi
Performance
1k
tokens
747.8
PP tok/s
27.4
TG tok/s
1369
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 747.8 | 27.4 | 20.4 GB | current |
| 4k | 891.0 | 26.4 | 21.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.4 | 1.00× |
| 2× | 45.4 | 1.66× |
| 4× | 89.4 | 3.26× |