Update README.md

README.md

@@ -86,11 +86,11 @@ July, 2025. This model is what started the **Impish** line of models. It had a l
 ## Impish_LLAMA_3B is available at the following quantizations:
 
 - Original: [FP16](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B)
-- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_GGUF) | [iMatrix_GGUF](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_iMatrix)
+- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_GGUF) | [iMatrix_GGUF](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_iMatrix) | [High-Attention](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_GGUF_HA) | [iMatrix-High-Attention](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_HA_NL)
 - EXL2: [4.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-4.0bpw) | [5.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-5.0bpw) | [6.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-6.0bpw) | [7.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-7.0bpw) | [8.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-8.0bpw)
 - GPTQ: [4-Bit-G32](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_GPTQ)
 - Specialized: [FP8](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_FP8)
-- Mobile (ARM): [Q4_0_X_X](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_ARM)
+- Mobile (ARM): [Q4_0](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_ARM) | [Q4_0_High-Attention](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_ARM_HA)