diff --git a/apps/librechat/release.yaml b/apps/librechat/release.yaml
index a7d5e58..04d5272 100644
--- a/apps/librechat/release.yaml
+++ b/apps/librechat/release.yaml
@@ -58,9 +58,15 @@ spec:
                   "Qwen2.5-VL-7B-Instruct-GGUF",
                   "Qwen2.5-VL-32B-Instruct-GGUF-IQ1_S",
                   "Qwen2.5-VL-32B-Instruct-GGUF-Q2_K_L",
+                  "Qwen3-VL-2B-Instruct-GGUF",
+                  "Qwen3-VL-2B-Instruct-GGUF-unslothish",
+                  "Qwen3-VL-2B-Thinking-GGUF",
                   "Qwen3-VL-4B-Instruct-GGUF",
                   "Qwen3-VL-4B-Instruct-GGUF-unslothish",
-                  "Qwen3-VL-4B-Thinking-GGUF"
+                  "Qwen3-VL-4B-Thinking-GGUF",
+                  "Qwen3-VL-8B-Instruct-GGUF",
+                  "Qwen3-VL-8B-Instruct-GGUF-unslothish",
+                  "Qwen3-VL-8B-Thinking-GGUF"
                 ]
               titleConvo: true
               titleModel: "gemma3-4b-novision"
diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index fd0c7b9..50c7d63 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -250,6 +250,26 @@ models:
         --no-warmup
         --port ${PORT}
 
+  "Qwen3-VL-2B-Instruct-GGUF":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-2B-Instruct-GGUF:Q8_0
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --temp 0.7
+        --top-p 0.85
+        --top-k 20
+        --min-p 0.05
+        --repeat-penalty 1.15
+        --frequency-penalty 0.5
+        --presence-penalty 0.4
+        --no-warmup
+        --port ${PORT}
+
   "Qwen3-VL-4B-Instruct-GGUF":
     ttl: 600
     cmd: |
@@ -270,6 +290,46 @@ models:
         --no-warmup
         --port ${PORT}
 
+  "Qwen3-VL-8B-Instruct-GGUF":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_M
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --temp 0.7
+        --top-p 0.85
+        --top-k 20
+        --min-p 0.05
+        --repeat-penalty 1.15
+        --frequency-penalty 0.5
+        --presence-penalty 0.4
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3-VL-2B-Instruct-GGUF-unslothish":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-2B-Instruct-GGUF:Q8_0
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --temp 0.7
+        --top-p 0.8
+        --top-k 20
+        --min-p 0.05
+        --repeat-penalty 1.15
+        --frequency-penalty 0.5
+        --presence-penalty 0.6
+        --no-warmup
+        --port ${PORT}
+
   "Qwen3-VL-4B-Instruct-GGUF-unslothish":
     ttl: 600
     cmd: |
@@ -290,6 +350,45 @@ models:
         --no-warmup
         --port ${PORT}
 
+  "Qwen3-VL-8B-Instruct-GGUF-unslothish":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_M
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --temp 0.7
+        --top-p 0.8
+        --top-k 20
+        --min-p 0.05
+        --repeat-penalty 1.15
+        --frequency-penalty 0.5
+        --presence-penalty 0.6
+        --no-warmup
+        --port ${PORT}
+
+  "Qwen3-VL-2B-Thinking-GGUF":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-2B-Thinking-GGUF:Q8_0
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --top-p 0.95
+        --top-k 20
+        --temp 1.0
+        --min-p 0.0
+        --repeat-penalty 1.0
+        --presence-penalty 0.0
+        --no-warmup
+        --port ${PORT}
+
   "Qwen3-VL-4B-Thinking-GGUF":
     ttl: 600
     cmd: |
@@ -308,3 +407,22 @@ models:
         --presence-penalty 0.0
         --no-warmup
         --port ${PORT}
+
+  "Qwen3-VL-8B-Thinking-GGUF":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf Qwen/Qwen3-VL-8B-Thinking-GGUF:Q4_K_M
+        --n-gpu-layers 99
+        --ctx-size 12288
+        --predict 4096
+        --flash-attn auto
+        --jinja
+        --top-p 0.95
+        --top-k 20
+        --temp 1.0
+        --min-p 0.0
+        --repeat-penalty 1.0
+        --presence-penalty 0.0
+        --no-warmup
+        --port ${PORT}