chris320211/flatquant-phi3-mini-4k-g52xlarge
Text Generation • Updated • 497
One library of quantized LLMs measured by quant-agent. Rank WikiText-2 in the GitHub library/ catalog, then download these repos.
Note FlatQuant · microsoft/Phi-3-mini-4k-instruct · g5.2xlarge · WikiText-2 ppl_ratio=1.1676
Note SmoothQuant · ibm-granite/granite-3.3-2b-instruct · g5.2xlarge · WikiText-2 ppl_ratio=1.0060
Note SmoothQuant · Qwen/Qwen2.5-1.5B-Instruct · g5.2xlarge · WikiText-2 ppl_ratio=1.0509
Note SmoothQuant · google/gemma-2-2b-it · g5.2xlarge · WikiText-2 ppl_ratio=1.0215