From 1e68450d8adf8ec7a3d63b33bbe15db8da6c1f84 Mon Sep 17 00:00:00 2001
From: Lumpiasty <arek.dzski@gmail.com>
Date: Sat, 28 Feb 2026 15:49:59 +0100
Subject: [PATCH] Add Qwen3.5-35-A3B model

---
 apps/llama/configs/config.yaml | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index 92b809f..cdf84e7 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -456,3 +456,30 @@ models:
         --repeat-penalty 1.0
         --no-warmup
         --port ${PORT}
+
+  "Qwen3.5-35B-A3B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 1.0
+        --min-p 0.00
+        --top-p 0.95
+        --top-k 20
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3.5-35B-A3B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 1.0
+        --min-p 0.00
+        --top-p 0.95
+        --top-k 20
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"