diff --git a/llama.cpp b/llama.cpp
index 49e4503c0..3c85945d7 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -3719,33 +3719,40 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
             } else if (name.find("attn_v.weight") != std::string::npos) {
                 if      (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
             } else if (tensor.name.find("attention.wv.weight") != std::string::npos) {
-                if      (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) {
+                if      (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K;
+                else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) {
                     new_type = i_attention_wv < 2 ? GGML_TYPE_Q5_K : GGML_TYPE_Q4_K;
                 }
                 else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
                 else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&
                         use_more_bits(i_attention_wv, n_attention_wv)) new_type = GGML_TYPE_Q6_K;
                 else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_S && i_attention_wv < 4) new_type = GGML_TYPE_Q5_K;
-                else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_S && i_attention_wv < 4) new_type = GGML_TYPE_Q5_K;
+                //else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_S && i_attention_wv < 4) new_type = GGML_TYPE_Q5_K;
                 else if (QK_K == 64 && (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_S || ftype == LLAMA_FTYPE_MOSTLY_Q3_K_S) &&
                         (i_attention_wv < n_attention_wv/8 || i_attention_wv >= 7*n_attention_wv/8)) new_type = GGML_TYPE_Q6_K;
                 ++i_attention_wv;
             } else if (name.find("ffn_down.weight") != std::string::npos) {
                 if      (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
             } else if (tensor.name.find("feed_forward.w2.weight") != std::string::npos) {
-                if      (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) {
+                if      (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K;
+                else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) {
                     new_type = i_feed_forward_w2 < 2 ? GGML_TYPE_Q5_K : GGML_TYPE_Q4_K;
                 }
                 else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
                 else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&
                          use_more_bits(i_feed_forward_w2, n_feed_forward_w2)) new_type = GGML_TYPE_Q6_K;
                 else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_S && i_feed_forward_w2 < 4) new_type = GGML_TYPE_Q5_K;
-                //else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_S && i_feed_forward_w2 < 4) new_type = GGML_TYPE_Q5_K;
                 ++i_feed_forward_w2;
             } else if (name.find("attn_output.weight") != std::string::npos) {
                 if      (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
+            } else if (tensor.name.find("attention.wo.weight") != std::string::npos) {
+                if      (ftype == LLAMA_FTYPE_MOSTLY_Q2_K  ) new_type = GGML_TYPE_Q3_K;
+                else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) new_type = GGML_TYPE_Q4_K;
                 else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
             }
+            else if (tensor.name.find("feed_forward.w") != std::string::npos && ftype == LLAMA_FTYPE_MOSTLY_Q2_K) {
+                new_type = GGML_TYPE_Q3_K;
+            }
             bool convert_incompatible_tensor = false;
             if (new_type == GGML_TYPE_Q2_K || new_type == GGML_TYPE_Q3_K || new_type == GGML_TYPE_Q4_K ||
                 new_type == GGML_TYPE_Q5_K || new_type == GGML_TYPE_Q6_K) {