community pool / model answer
RWKV7-Goose-World3-2.9B-HF
chat · RWKV/RWKV7-Goose-World3-2.9B-HF
47.2 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GTX 1060 3GB | 4-bit | 31.6 tok/s | reported | 2,900 | - GB | 2,048 | llama.cpp |
| RX 570 4GB ×2 | 4-bit | 47.2 tok/s | measured | 262 | - 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.