community pool / model answer

Qwopus-MoE-35B-A3B-GGUF

chat · samuelcardillo/Qwopus-MoE-35B-A3B-GGUF

74.4 tok/s · model median · 6 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Ryzen AI Max 395 128GB4-bit54.7 tok/sreported27,136- GB32,768llama.cpp
Ryzen AI Max 395 64GB4-bit74.6 tok/smeasured1,27220.4 GB8,192llama.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.