ThomasBaruzier
/

Qwen2.5-7B-Instruct-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Qwen2.5-7B-Instruct-GGUF / perplexity.md

ThomasBaruzier's picture

Upload perplexity.md

66cb1be verified 2 months ago

|

history blame contribute delete

197 Bytes


	Qwen2.5-7B-Instruct
	Quant Size (MB) PPL Size (%) Accuracy (%) PPL error rate
	IQ1_S 1816 29.2065 0.23022
	IQ1_M 1948 17.5876 0.13256
	IQ2_XXS 2168 13.0997 0.10138
	IQ2_XS 2355 10.6611 0.07823