← Back to community benchmarks
Qwen3.5-27B-Architect-Polaris-Heretic-mxfp4
Performance
16k
tokens
772.7
PP tok/s
30.6
TG tok/s
21204
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 772.7 | 30.6 | 18.4 GB | current |
| 32k | 675.1 | 26.3 | 20.9 GB | view |