community pool / model answer

WebWorld-14B-GGUF

chat · DhruvalLabs/WebWorld-14B-GGUF

29.3 tok/s · model median · 20 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit27.2 tok/smeasured2,551- GB65,536llama.cpp
RTX 3060 12GB ×24-bit32.3 tok/smeasured3,29910.9 GB32,768llama.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.