From c976c7a0507ceb609783cf8099f3bb940083b55e Mon Sep 17 00:00:00 2001
From: zunami <c.rebler@gmail.com>
Date: Wed, 27 May 2026 08:33:06 +0200
Subject: [PATCH] Create qwen3.5-9b-q4_k_m.yaml

---
 models/ollama/qwen3.5-9b-q4_k_m.yaml | 52 ++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 models/ollama/qwen3.5-9b-q4_k_m.yaml

diff --git a/models/ollama/qwen3.5-9b-q4_k_m.yaml b/models/ollama/qwen3.5-9b-q4_k_m.yaml
new file mode 100644
index 0000000..bb181b7
--- /dev/null
+++ b/models/ollama/qwen3.5-9b-q4_k_m.yaml
@@ -0,0 +1,52 @@
+provider: ollama
+authType: api_key
+model: qwen3.5:9b-q4_K_M
+params:
+  - path: max_tokens
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    group: generation_length
+    type: integer
+    range:
+      min: 1
+
+  - path: temperature
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    group: sampling
+    type: number
+    default: 0.7
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+
+  - path: top_p
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    group: sampling
+    type: number
+    default: 0.9
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+
+  - path: top_k
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    group: sampling
+    type: integer
+    default: 40
+    range:
+      min: 1
+
+  - path: num_ctx
+    label: Context length
+    description: Controls the context window size in tokens.
+    group: generation_length
+    type: integer
+    default: 32768
+    range:
+      min: 2048
+      max: 131072