community pool / model answer
WebWorld-8B-GGUF
chat · DhruvalLabs/WebWorld-8B-GGUF
51.4 tok/s · model median · 15 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 43.7 tok/s | measured | 370 | - GB | 131,072 | llama.cpp |
| RTX 3060 12GB ×2 | 4-bit | 54 tok/s | measured | 1,886 | 7.1 GB | 32,768 | 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.