From 46a7e24932c9a563b5f048dc3640a7fd2ae1cbc3 Mon Sep 17 00:00:00 2001
From: Lumpiasty <arek.dzski@gmail.com>
Date: Fri, 6 Mar 2026 23:07:02 +0100
Subject: [PATCH] add 2B, 4B, 9B versions of Qwen3.5 in thinking + nonthinking
 variants

---
 apps/llama/configs/config.yaml | 94 ++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)

diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index 1ae1384..c7fde83 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -579,3 +579,97 @@ models:
         --no-warmup
         --port ${PORT}
         --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-0.8B-GGUF:Q4_K_XL":
+    ttl: 0
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_XL
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3.5-2B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3.5-2B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-4B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3.5-4B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-9B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3.5-9B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"