fix(gallery): remove unsupported Instella-MoE models

Both GGUF entries select llama-cpp, whose pinned revision does not
recognize instella-moe. Remove the broken install options and document
why they are unavailable until LocalAI ships a compatible backend.

Refs #11681

Assisted-by: Codex:GPT-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/cpp/audio-cpp/generation_request.cpp

@@ -135,13 +135,6 @@ build_tts_request(const backend::TTSRequest &request,
         task.options["language"] = request.language();
     }
 
-    // Saved voice profiles send ref_text; Fish Audio reads reference_text.
-    // Derive the alias before copying params so an explicit canonical key wins.
-    const auto reference_text = request.params().find("ref_text");
-    if (reference_text != request.params().end()) {
-        task.options["reference_text"] = reference_text->second;
-    }
-
     // LAST, so an explicit params entry wins over anything derived above. That
     // matters for "caption": a caller who sets params[caption] has named the
     // exact string they want, and it must not be overwritten by `instructions`.

backend/cpp/audio-cpp/generation_request_ctest.cpp

@@ -375,40 +375,6 @@ static void test_tts_language_and_params() {
           "tts params: an explicit param overrides the derived caption");
 }
 
-static void test_tts_reference_transcript() {
-    backend::TTSRequest request;
-    request.set_text("New speech to generate.");
-    request.set_voice("reference.wav");
-    (*request.mutable_params())["ref_text"] = "The saved voice transcript.";
-
-    const auto task = build_tts_request(request, clip(24000, 1));
-    check(option_or(task.options, "reference_text", "") ==
-              "The saved voice transcript.",
-          "tts reference: saved transcript reaches Fish Audio's option");
-    check(option_or(task.options, "ref_text", "") ==
-              "The saved voice transcript.",
-          "tts reference: original transcript parameter is preserved");
-    check(task.text_input->text == "New speech to generate.",
-          "tts reference: transcript does not replace synthesis text");
-
-    (*request.mutable_params())["reference_text"] = "Explicit transcript.";
-    const auto explicit_task = build_tts_request(request, clip(24000, 1));
-    check(option_or(explicit_task.options, "reference_text", "") ==
-              "Explicit transcript.",
-          "tts reference: explicit canonical parameter wins over alias");
-
-    (*request.mutable_params())["reference_text"] = "";
-    const auto empty_task = build_tts_request(request, clip(24000, 1));
-    check(has_key(empty_task.options, "reference_text") &&
-              empty_task.options.at("reference_text").empty(),
-          "tts reference: explicit empty canonical parameter is preserved");
-
-    request.mutable_params()->clear();
-    const auto missing_task = build_tts_request(request, clip(24000, 1));
-    check(!has_key(missing_task.options, "reference_text"),
-          "tts reference: no transcript is invented when none was supplied");
-}
-
 static void test_sound_generation_minimal() {
     backend::SoundGenerationRequest request;
     request.set_text("a distant thunderstorm");
@@ -596,7 +562,6 @@ int main() {
     test_tts_empty_language_is_not_a_language();
     test_tts_clip_and_instructions();
     test_tts_language_and_params();
-    test_tts_reference_transcript();
     test_sound_generation_minimal();
     test_sound_generation_full();
     test_transform_text_absent();

docs/content/features/audio-cpp.md

@@ -217,12 +217,6 @@ voice conversion from the same weights.
 
 ## Family notes
 
-- **Fish Audio voice cloning**: save a reference clip with its transcript in the
-  Voice Library, then select **Use in Text to Speech**. The backend accepts
-  `params.ref_text` as an alias for `params.reference_text` in both ordinary and
-  streaming speech requests. If you supply both parameters, `reference_text`
-  takes precedence. For direct requests with a reference file in `voice`, supply
-  its transcript in one of these parameters.
 - **Supertonic**: use the `orig` GGUF package, whose weights are f32. The f16 package was
   observed to reach `ggml_concat` with mismatched operand types and take the backend
   process down with `SIGABRT` on the first request, rather than returning an error.

docs/content/features/model-gallery.md

@@ -23,6 +23,17 @@ GPT and text generation models might have a license which is not permissive for
 
 ![output](https://github.com/mudler/LocalAI/assets/2420543/7b16676e-d5b1-4c97-89bd-9fa5065c21ad)
 
+## Instella-MoE availability
+
+The gallery excludes `instella-moe-16b-a3b-think` and
+`instella-moe-16b-a3b-think-q8` because the packaged llama.cpp backend does not
+support their `instella-moe` architecture. Loading these GGUF files fails with
+`unknown model architecture: 'instella-moe'`.
+
+The entries can return after LocalAI ships a compatible backend. See
+[the compatibility issue](https://github.com/mudler/LocalAI/issues/11681) and
+[upstream llama.cpp support](https://github.com/ggml-org/llama.cpp/pull/26467).
+
 ## Useful Links and resources
 
 - [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) - here you can find a list of the most performing models on the Open LLM benchmark. Keep in mind models compatible with LocalAI must be quantized in the `gguf` format.

gallery/index.yaml

@@ -6133,90 +6133,6 @@
     - filename: llama-cpp/models/DeepSeek-V4-Pro-0813-UD-Q4_K_XL/DeepSeek-V4-Pro-0813-UD-Q4_K_XL-00020-of-00020.gguf
       uri: huggingface://unsloth/DeepSeek-V4-Pro-0813-GGUF/UD-Q4_K_XL/DeepSeek-V4-Pro-0813-UD-Q4_K_XL-00020-of-00020.gguf
       sha256: 5978999836fd1fe7ad7da6232a70981bd7f98274ed71d3b06652ba42c7b46031
-- name: instella-moe-16b-a3b-think
-  url: github:mudler/LocalAI/gallery/virtual.yaml@master
-  urls:
-    - https://huggingface.co/amd/Instella-MoE-16B-A3B-Think
-    - https://huggingface.co/DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF
-  description: |
-    AMD Instella-MoE-16B-A3B-Think is a reasoning and instruction-following
-    mixture-of-experts model with 16 billion total parameters and 3 billion
-    active parameters. It supports long-form reasoning, chat, coding, and tool
-    use. This entry uses the Q4_K_M GGUF quantization.
-  license: other
-  tags:
-    - llm
-    - gguf
-    - deepseek-v3
-    - moe
-    - reasoning
-    - thinking
-    - coding
-    - tool-use
-    - cpu
-    - gpu
-  last_checked: "2026-08-03"
-  variants:
-    - model: instella-moe-16b-a3b-think-q8
-  overrides:
-    backend: llama-cpp
-    function:
-      automatic_tool_parsing_fallback: true
-      grammar:
-        disable: true
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q4_K_M.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q4_K_M.gguf
-      sha256: f776ddfee5dc6c808265c3f0a9c1b384c98058bfa551fe5df656fe712eb4c7f3
-      uri: huggingface://DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF/Q4_K_M/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q4_K_M.gguf
-- name: instella-moe-16b-a3b-think-q8
-  url: github:mudler/LocalAI/gallery/virtual.yaml@master
-  urls:
-    - https://huggingface.co/amd/Instella-MoE-16B-A3B-Think
-    - https://huggingface.co/DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF
-  description: |
-    AMD Instella-MoE-16B-A3B-Think is a reasoning and instruction-following
-    mixture-of-experts model with 16 billion total parameters and 3 billion
-    active parameters. It supports long-form reasoning, chat, coding, and tool
-    use. This entry uses the near-lossless Q8_0 GGUF quantization.
-  license: other
-  tags:
-    - llm
-    - gguf
-    - deepseek-v3
-    - moe
-    - reasoning
-    - thinking
-    - coding
-    - tool-use
-    - cpu
-    - gpu
-  last_checked: "2026-08-03"
-  overrides:
-    backend: llama-cpp
-    function:
-      automatic_tool_parsing_fallback: true
-      grammar:
-        disable: true
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q8_0.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q8_0.gguf
-      sha256: 6bff0a99d06be8ecf7d9c7f65584bfc2b24526ab0bab32dbfe7dde4237cd7c33
-      uri: huggingface://DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF/Q8_0/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q8_0.gguf
 - name: "parable-granite-4.1-3b-claude-fable-5"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: