community pool / model answer

Qwythos-9B-Claude-Mythos-5-1M-GGUF

chat · empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

53.6 tok/s · model median · 4 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 7700 XT 12GB4-bit53.6 tok/sreported197- GB2,048vllm
Ryzen AI Max 395 128GB4-bit35.3 tok/sreported1457.4 GB4,096llama.cpp
Ryzen AI Max 395 128GB5-bit22.3 tok/sreported74,0978.1 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.