← Back to community benchmarks
Qwen3.6-27B-Architect-Polaris-Fable-qx64-hi
Performance
1k
tokens
87.3
PP tok/s
15.5
TG tok/s
11730
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
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 | 87.3 | 15.5 | 20.4 GB | current |
| 4k | 89.4 | 14.8 | 21.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.5 | 1.00× |
| 2× | 17.9 | 1.15× |
| 4× | 19.8 | 1.28× |