community pool / model answer
DeepSeek-V4-Flash-ROCMFPX
chat · Lucebox/DeepSeek-V4-Flash-ROCMFPX
77.5 tok/s · model median · 22 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB | 4-bit | 78.9 tok/s | measured | - | - GB | 131,072 | llama.cpp |
| Ryzen AI Max 395 128GB | 2-bit | 30.1 tok/s | reported | - | - GB | 8,192 | lucebox |
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.