From 04610cc6e23cd1b21cdbcc028241e3d48eba7189 Mon Sep 17 00:00:00 2001
From: Aleksandr Bogomiakov <git@hexor.cy>
Date: Thu, 15 Oct 2026 01:19:37 +0100
Subject: [PATCH] Changed llama model unsloth/Qwen3.8-27B-GGUF:UD-Q6_K ->
 unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q6_K

---
 k8s-ng/apps/llamacpp/configmap.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/k8s-ng/apps/llamacpp/configmap.yaml b/k8s-ng/apps/llamacpp/configmap.yaml
index 6a9e33c..7712f04 100644
--- a/k8s-ng/apps/llamacpp/configmap.yaml
+++ b/k8s-ng/apps/llamacpp/configmap.yaml
@@ -8,7 +8,8 @@ data:
   LLAMA_ARG_PORT: "8080"
   # The model is chosen here: <hf-user>/<repo>:<quant>. It is downloaded into
   # /models on first start; changing it restarts the pod (reloader).
-  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.8-27B-GGUF:UD-Q6_K"
+  #LLAMA_ARG_HF_REPO: "unsloth/Qwen3.8-27B-GGUF:UD-Q6_K"
+  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q6_K"
   LLAMA_ARG_CTX_SIZE: "131072"
   LLAMA_ARG_N_GPU_LAYERS: all
   LLAMA_ARG_FLASH_ATTN: "on"