From cfd2d84b47729f299bb137c047857741975f3c5f Mon Sep 17 00:00:00 2001
From: Alexander Rogov <i_am@rogov.al>
Date: Sat, 29 Aug 2026 15:44:12 +0300
Subject: [PATCH] small model

---
 manifests/llama/main.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/manifests/llama/main.yaml b/manifests/llama/main.yaml
index 0d7126a..03a6a14 100644
--- a/manifests/llama/main.yaml
+++ b/manifests/llama/main.yaml
@@ -27,9 +27,9 @@ spec:
             - name: HF_HOME
               value: /models/.hf
             - name: MODEL_REPO
-              value: "byteshape/Qwen3.8-27B-GGUF"
+              value: "byteshape/Qwen3.5-9B-GGUF"
             - name: MODEL_FILE
-              value: "Qwen3.8-27B-IQ3_S-3.44bpw.gguf"
+              value: "Qwen3.5-9B-Q5_K_S-5.10bpw.gguf"
             # optional, only if you need gated/private models
             # - name: HUGGING_FACE_HUB_TOKEN
             #   valueFrom:
@@ -82,7 +82,7 @@ spec:
           image: ghcr.io/ggml-org/llama.cpp:server-vulkan
           args:
             - "--model"
-            - "/models/Qwen3.8-27B-IQ3_S-3.44bpw.gguf"
+            - "/models/Qwen3.5-9B-Q5_K_S-5.10bpw.gguf"
             - "--host"
             - "0.0.0.0"
             - "--port"