Add IQ3_K now with ik_llama.cpp PR735

README.md

@@ -195,6 +195,60 @@ custom=$(
 
 </details>
 
+## `IQ3_K` 14.509 GiB (4.082 BPW)
+Final estimate: PPL = 9.6849 +/- 0.0768
+
+<details>
+
+<summary>👈 Secret Recipe</summary>
+
+```bash
+#!/usr/bin/env bash
+
+custom="
+# 48 Repeating Layers [0-47]
+
+# Attention
+blk\.(0)\.attn_q.*=q8_0
+blk\.(0)\.attn_k.*=q8_0
+blk\.(0)\.attn_v.*=q8_0
+blk\.(0)\.attn_output.*=q8_0
+
+blk\..*\.attn_q.*=iq5_k
+blk\..*\.attn_k.*=iq6_k
+blk\..*\.attn_v.*=iq6_k
+blk\..*\.attn_output.*=iq5_k
+
+# Routed Experts
+blk\.(0|47)\.ffn_down_exps\.weight=q8_0
+blk\.(0|47)\.ffn_(gate|up)_exps\.weight=q8_0
+
+blk\..*\.ffn_down_exps\.weight=iq4_k
+blk\..*\.ffn_(gate|up)_exps\.weight=iq3_k
+
+# Non-Repeating Layers
+token_embd\.weight=iq4_k
+output\.weight=iq6_k
+"
+
+custom=$(
+  echo "$custom" | grep -v '^#' | \
+  sed -Ez 's:\n+:,:g;s:,$::;s:^,::'
+)
+
+./build/bin/llama-quantize \
+    --custom-q "$custom" \
+    --imatrix /mnt/raid/models/ubergarm/Qwen3-Coder-30B-A3B-Instruct-GGUF/imatrix-Qwen3-Coder-30B-A3B-Instruct-BF16.dat \
+    /mnt/raid/models/ubergarm/Qwen3-Coder-30B-A3B-Instruct-GGUF/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf \
+    /mnt/raid/models/ubergarm/Qwen3-Coder-30B-A3B-Instruct-GGUF/Qwen3-Coder-30B-A3B-Instruct-PR735-IQ3_K.gguf \
+    IQ3_K \
+    192
+```
+
+</details>
+
+
+
 ## `IQ3_KS` 13.633 GiB (3.836 BPW)
 Final estimate: PPL = 9.7940 +/- 0.07795