diff --git a/src/llama.cpp b/src/llama.cpp
index e6f303d31..f798dcdfe 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -15348,11 +15348,11 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
     } else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS || ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ1_S ||
                ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || ftype == LLAMA_FTYPE_MOSTLY_IQ2_M    || ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) {
         if (name.find("attn_v.weight") != std::string::npos) {
-            if (qs.model.hparams.n_gqa() >= 4 || qs.model.hparams.n_expert >= 4) new_type = GGML_TYPE_Q4_K;
+            if (qs.model.hparams.n_gqa() >= 2 || qs.model.hparams.n_expert >= 2) new_type = GGML_TYPE_Q4_K;
             else new_type = ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || ftype == LLAMA_FTYPE_MOSTLY_IQ2_M ? GGML_TYPE_IQ3_S : GGML_TYPE_Q2_K;
             ++qs.i_attention_wv;
         }
-        else if (qs.model.hparams.n_expert == 8 && name.find("attn_k.weight") != std::string::npos) {
+        else if (qs.model.hparams.n_expert >= 8 && name.find("attn_k.weight") != std::string::npos) {
             new_type = GGML_TYPE_Q4_K;
         }
         else if (name.find("ffn_down") != std::string::npos) {
@@ -15366,7 +15366,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
                 new_type = GGML_TYPE_Q5_K;
             } else {
                 if (ftype == LLAMA_FTYPE_MOSTLY_IQ1_S || ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) new_type = GGML_TYPE_IQ2_XXS;
-                else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || ftype == LLAMA_FTYPE_MOSTLY_IQ2_M) new_type = GGML_TYPE_IQ3_S;
+                else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || ftype == LLAMA_FTYPE_MOSTLY_IQ2_M) new_type = GGML_TYPE_IQ3_XXS;
             }
         }
     } else if (name.find("attn_v.weight") != std::string::npos) {