From d28ccf32b58392cc47912da35f6350c19b5207d5 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot <bot-opensource@localaisrl.com>
Date: Mon, 3 Aug 2026 19:02:10 +0200
Subject: [PATCH] gallery: add Qwen3.6 14B FableVibes variants (#11317)

Add Q4_K_M and Q8_0 llama.cpp entries with the shared Q8_0 multimodal projector.

Assisted-by: Codex:gpt-5

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
---
 gallery/index.yaml | 79 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 32ad2a436..76013afd0 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1387,6 +1387,85 @@
     - filename: llama-cpp/mmproj/Qwythos-9B-v2-MTP-Q4_K_M/mmproj-Qwythos-9B-v2-BF16.gguf
       sha256: 0d1687cb33124c78acab788b342d4a2eaf85b3035e87c3abe4ee9d0b84ddb4f5
       uri: https://huggingface.co/empero-ai/Qwythos-9B-v2-GGUF/resolve/main/mmproj-Qwythos-9B-v2-BF16.gguf
+- &qwen3-6-14b-a3b-fablevibes
+  name: "qwen3.6-14b-a3b-fablevibes"
+  variants:
+    - model: qwen3.6-14b-a3b-fablevibes-q8
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/tvall43/Qwen3.6-14B-A3B-FableVibes
+    - https://huggingface.co/tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF
+  description: |
+    Qwen3.6-14B-A3B-FableVibes is an Apache-2.0 mixture-of-experts reasoning
+    model distilled from Fable 5 and Claude Opus traces, with additional tool
+    calling and coding data. It retains Qwen 3.6 vision support while pruning
+    the 35B-A3B base to a 14B consumer-oriented footprint. This default entry
+    uses the recommended Q4_K_M GGUF quantization and its Q8_0 multimodal
+    projector.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - moe
+    - reasoning
+    - thinking
+    - vision
+    - multimodal
+  last_checked: "2026-08-03"
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwen3.6-14B-A3B-FableVibes/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Qwen3.6-14B-A3B-FableVibes/Qwen3.6-14B-A3B-FableVibes-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwen3.6-14B-A3B-FableVibes/Qwen3.6-14B-A3B-FableVibes-Q4_K_M.gguf
+      sha256: 21aa4b0b28090469e8a319c889451df2f1ea6aad27ac3818c8c8a86f86d5bc9e
+      uri: huggingface://tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF/Qwen3.6-14B-A3B-FableVibes-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/Qwen3.6-14B-A3B-FableVibes/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
+      sha256: ca27dbf0c65a7232e9458bfdda8bc45efc09ab60e4cc6f58ea0c7b7cc2253257
+      uri: huggingface://tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
+- !!merge <<: *qwen3-6-14b-a3b-fablevibes
+  name: "qwen3.6-14b-a3b-fablevibes-q8"
+  variants: []
+  description: |
+    Qwen3.6-14B-A3B-FableVibes is an Apache-2.0 mixture-of-experts reasoning
+    model distilled from Fable 5 and Claude Opus traces, with additional tool
+    calling and coding data. This entry uses the near-lossless Q8_0 GGUF
+    quantization and its matching Q8_0 multimodal projector.
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwen3.6-14B-A3B-FableVibes-Q8_0/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Qwen3.6-14B-A3B-FableVibes-Q8_0/Qwen3.6-14B-A3B-FableVibes-Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwen3.6-14B-A3B-FableVibes-Q8_0/Qwen3.6-14B-A3B-FableVibes-Q8_0.gguf
+      sha256: ddea86093b863215fa75969d81df494fafdb0e6c4a65af557ed3a710e2238e58
+      uri: huggingface://tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF/Qwen3.6-14B-A3B-FableVibes-Q8_0.gguf
+    - filename: llama-cpp/mmproj/Qwen3.6-14B-A3B-FableVibes-Q8_0/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
+      sha256: ca27dbf0c65a7232e9458bfdda8bc45efc09ab60e4cc6f58ea0c7b7cc2253257
+      uri: huggingface://tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF/Qwen3.6-14B-A3B-FableVibes-mmproj-Q8_0.gguf
 - name: "qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: