Update README.md

README.md

@@ -4,6 +4,13 @@ language:
 - en
 pipeline_tag: text-generation
 ---
+
+## SmallThinker-4BA0.6B-Instruct-GGUF
+
+- GGUF models with `.gguf` suffix can used with [*llama.cpp* framwork](https://github.com/wdl339/llama.cpp/tree/smallthinker).
+
+- GGUF models with `.powerinfer.gguf` suffix are integrated with fused sparse FFN operators and sparse LM head operators. These models are only compatible to [*powerinfer* framwork](https://github.com/SJTU-IPADS/PowerInfer/tree/main/smallthinker).
+
 ## Introduction
 
 SmallThinker is a family of **on-device native** Mixture-of-Experts (MoE) language models specially designed for local deployment,