community pool / model answer

InternVL3-8B

chat · OpenGVLab/InternVL3-8B

65 tok/s · model median · 35 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit57.3 tok/smeasured325- GB131,072llama.cpp
RTX 3060 Ti 8GB4-bit68.1 tok/smeasured2716.7 GB131,072llama.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.