From 6f77dbb9d9effdf62d9f3948d780c20ebe94050c Mon Sep 17 00:00:00 2001
From: Hitonabi <Hitonabi@dreivontanke.ddnsfree.com>
Date: Tue, 7 Jul 2026 17:18:31 +0200
Subject: [PATCH] chore(config): remove missing Qwen3.5-122B and Qwen3-VL-8B,
 promote gpt-oss-120b

---
 deploy/llama-swap.config.yaml | 31 ++++++-------------------------
 1 file changed, 6 insertions(+), 25 deletions(-)

diff --git a/deploy/llama-swap.config.yaml b/deploy/llama-swap.config.yaml
index c30e5ec..a0b8672 100644
--- a/deploy/llama-swap.config.yaml
+++ b/deploy/llama-swap.config.yaml
@@ -19,17 +19,6 @@ models:
       out: [text]
       tools: true
       context: 65536
-  Qwen3.5-122B-A10B:
-    cmd: |
-      llama-server -m /srv/models/Qwen3.5-122B-A10B-GGUF/Q4_K_M/Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
-    ttl: 600
-    aliases:
-    - heavy
-    capabilities:
-      in: [text]
-      out: [text]
-      tools: true
-      context: 32768
   Qwen3-Coder-Next:
     cmd: |
       llama-server -m /srv/models/Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
@@ -41,17 +30,6 @@ models:
       out: [text]
       tools: true
       context: 131072
-  Qwen3-VL-8B-Instruct:
-    cmd: |
-      llama-server -m /srv/models/Qwen3-VL-8B-Instruct-GGUF/Qwen3VL-8B-Instruct-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --mmproj /srv/models/Qwen3-VL-8B-Instruct-GGUF/mmproj-Qwen3VL-8B-Instruct-F16.gguf --jinja
-    # ttl 0 (03.07.): Mitglied des Immer-bereit-Sets — ein Selbstauslöser widerspräche dem UI-Versprechen.
-    ttl: 0
-    aliases:
-    - vision
-    capabilities:
-      in: [text, image]
-      out: [text]
-      context: 32768
   Qwen3-Embedding-0.6B:
     cmd: |
       llama-server -m /srv/models/Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf --host 127.0.0.1 --port ${PORT} --embedding --pooling last -ngl 999 -fa on --no-mmap -c 8192
@@ -70,11 +48,12 @@ models:
       tools: true
       context: 131072
   gpt-oss-120b:
-    # heavy-Kandidat (Bench 02.07.: tg 54-55 t/s vs. Qwen3.5-122B 23,5 t/s = 2,3x, 60 statt
-    # 73 GB). Noch OHNE heavy-Alias — erst Qualitaets-Check (deutsch/Reasoning), dann Entscheid.
+    # Wurde am 07.07. offiziell zum heavy Modell befördert.
     cmd: |
       llama-server -m /srv/models/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00001-of-00003.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
     ttl: 600
+    aliases:
+    - heavy
     capabilities:
       in: [text]
       out: [text]
@@ -87,6 +66,8 @@ models:
     cmd: |
       llama-server -m /srv/models/Qwen3-VL-30B-A3B-Instruct-GGUF/Qwen3-VL-30B-A3B-Instruct-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --mmproj /srv/models/Qwen3-VL-30B-A3B-Instruct-GGUF/mmproj-F16.gguf --jinja
     ttl: 0
+    aliases:
+    - vision
     capabilities:
       in: [text, image]
       out: [text]
@@ -111,5 +92,5 @@ groups:
     persistent: true
     members:
     - Qwen3-Embedding-0.6B
-    - Qwen3-VL-8B-Instruct
+    - Qwen3-VL-30B-A3B-Instruct
     - Qwen3.6-35B-A3B