community pool / model answer

Llama-3.1-WhiteRabbitNeo-2-8B

chat · WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-8B

50.6 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5000 16GB4-bit50.6 tok/sreported-9.7 GB65,536llama.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.