community pool / model answer

QUEST-30B-RL-B70-Turbo-GGUF

chat · Frosty40/QUEST-30B-RL-B70-Turbo-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B60 24GB5-bit77.2 tok/sreported513- GB2,048llama.cpp
Arc Pro B70 32GB5-bit8.8 tok/smeasured382- GB129,325llama.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.