localai-org-maint-bot · Oct 22, 2026 · Oct 23, 2026 · Oct 24, 2026 · Oct 25, 2026
diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
@@ -622,6 +622,18 @@ where:
 - `bert-embeddings` is the model name in the gallery
   (read its [config here](https://github.com/mudler/LocalAI/blob/master/gallery/index.yaml)).
 
+### Tess 4.5 27B
+
+Install `tess-4.5-27b-q4` for coding, reasoning, tool use, and image input
+with llama.cpp. The gallery groups Q4_K_M, Q6_K, and Q8_0 builds as variants.
+Each build includes the F16 vision projector and uses a 32,768-token context
+by default. These entries do not enable MTP speculative decoding or download
+the separate draft heads.
+
+```bash
+local-ai models install tess-4.5-27b-q4
+```
+
 ### Model variants
 
 Some gallery entries offer several builds of the same model: different

diff --git a/gallery/index.yaml b/gallery/index.yaml
@@ -3,6 +3,147 @@
 # written by scripts/models/cmd/modelcatalog and stays only so releases before
 # the cutover keep working. CI fails when it differs from the generated copy:
 #   go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: tess-4.5-27b-q4
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q4_K_M GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  files:
+    - filename: Tess-4.5-27B-Q4_K_M.gguf
+      sha256: 7a3157e2d4ab96a2abcee99a986bea11cfe282b58815ec676c5abe7e6a92d8dc
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q4_K_M.gguf
+    - filename: mmproj-Tess-4.5-27B-F16.gguf
+      sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: mmproj-Tess-4.5-27B-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: Tess-4.5-27B-Q4_K_M.gguf
+      temperature: 1.0
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  variants:
+    - model: tess-4.5-27b-q6
+    - model: tess-4.5-27b-q8
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: tess-4.5-27b-q6
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q6_K GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  files:
+    - filename: Tess-4.5-27B-Q6_K.gguf
+      sha256: 515a2a0339bbb6fa9083cf347755c1a08acb735a43ec1e20f6c361da9491f43b
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q6_K.gguf
+    - filename: mmproj-Tess-4.5-27B-F16.gguf
+      sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: mmproj-Tess-4.5-27B-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: Tess-4.5-27B-Q6_K.gguf
+      temperature: 1.0
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: tess-4.5-27b-q8
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q8_0 GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  files:
+    - filename: Tess-4.5-27B-Q8_0.gguf
+      sha256: 5e97564e427b8672c7e69e119534600b29cb1c1677381cd355be3d140c8aae7a
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q8_0.gguf
+    - filename: mmproj-Tess-4.5-27B-F16.gguf
+      sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+      uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: mmproj-Tess-4.5-27B-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: Tess-4.5-27B-Q8_0.gguf
+      temperature: 1.0
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
 - url: github:mudler/LocalAI/gallery/virtual.yaml@master
   name: adavar-3b-q4
   description: |

diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml
@@ -4,6 +4,171 @@
 # changes and never edit it by hand. CI fails when it is stale. A build from
 # master reads it as the default model source; a tagged build reads the gallery
 # until the release cutover.
+- kind: model
+  id: tess-4.5-27b-q4
+  name: tess-4.5-27b-q4
+  version: 0.0.0-gallery.c7df49b0fa37
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q4_K_M GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: Tess-4.5-27B-Q4_K_M.gguf
+        sha256: 7a3157e2d4ab96a2abcee99a986bea11cfe282b58815ec676c5abe7e6a92d8dc
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q4_K_M.gguf
+      - filename: mmproj-Tess-4.5-27B-F16.gguf
+        sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 32768
+      function:
+        automatic_tool_parsing_fallback: true
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+        - vision
+      mmproj: mmproj-Tess-4.5-27B-F16.gguf
+      options:
+        - use_jinja:true
+      parameters:
+        model: Tess-4.5-27B-Q4_K_M.gguf
+        temperature: 1.0
+        top_k: 20
+        top_p: 0.95
+      template:
+        use_tokenizer_template: true
+    variants:
+      - model: tess-4.5-27b-q6
+      - model: tess-4.5-27b-q8
+- kind: model
+  id: tess-4.5-27b-q6
+  name: tess-4.5-27b-q6
+  version: 0.0.0-gallery.636b28a09c32
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q6_K GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: Tess-4.5-27B-Q6_K.gguf
+        sha256: 515a2a0339bbb6fa9083cf347755c1a08acb735a43ec1e20f6c361da9491f43b
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q6_K.gguf
+      - filename: mmproj-Tess-4.5-27B-F16.gguf
+        sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 32768
+      function:
+        automatic_tool_parsing_fallback: true
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+        - vision
+      mmproj: mmproj-Tess-4.5-27B-F16.gguf
+      options:
+        - use_jinja:true
+      parameters:
+        model: Tess-4.5-27B-Q6_K.gguf
+        temperature: 1.0
+        top_k: 20
+        top_p: 0.95
+      template:
+        use_tokenizer_template: true
+- kind: model
+  id: tess-4.5-27b-q8
+  name: tess-4.5-27b-q8
+  version: 0.0.0-gallery.b120ec5f9e63
+  description: |
+    Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
+    This Q8_0 GGUF build includes the F16 vision projector and uses
+    llama.cpp with the embedded chat template. Speculative decoding is disabled.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/migtissera/Tess-4.5-27B
+    - https://huggingface.co/migtissera/Tess-4.5-27B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - coding
+    - reasoning
+    - vision
+    - multimodal
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: Tess-4.5-27B-Q8_0.gguf
+        sha256: 5e97564e427b8672c7e69e119534600b29cb1c1677381cd355be3d140c8aae7a
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/Tess-4.5-27B-Q8_0.gguf
+      - filename: mmproj-Tess-4.5-27B-F16.gguf
+        sha256: ae93dc35b2bf3a7730fa518db6f1e8d7c624363643f61d85eef8655b671257bb
+        uri: https://huggingface.co/migtissera/Tess-4.5-27B-GGUF/resolve/af17a3f0de2b8557849c1b6fcc303d3160052450/mmproj-Tess-4.5-27B-F16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 32768
+      function:
+        automatic_tool_parsing_fallback: true
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+        - vision
+      mmproj: mmproj-Tess-4.5-27B-F16.gguf
+      options:
+        - use_jinja:true
+      parameters:
+        model: Tess-4.5-27B-Q8_0.gguf
+        temperature: 1.0
+        top_k: 20
+        top_p: 0.95
+      template:
+        use_tokenizer_template: true
 - kind: model
   id: adavar-3b-q4
   name: adavar-3b-q4