community pool / model answer
Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED
chat · jcbtc/Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED
92.3 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Ryzen AI Max 395 128GB | 4-bit | 132.3 tok/s | reported | 105 | - GB | 2,048 | llama.cpp |
| Ryzen AI Max 395 128GB | 16-bit | 52.2 tok/s | reported | 339 | - GB | 2,048 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.