community pool / model answer

Qwythos-9B-v2-GGUF

chat · empero-ai/Qwythos-9B-v2-GGUF

54.6 tok/s · model median · 30 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit51.1 tok/sreported-5.8 GB32,768llama.cpp
RTX 3060 12GB ×24-bit53.2 tok/smeasured4569.8 GB131,072llama.cpp
RTX 3090 24GB4-bit78.5 tok/smeasured2,549- GB131,072llama.cpp
RX 7700 XT 12GB4-bit49.8 tok/sreported305- GB2,048vllm

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.