From f3818444037a9ac10a2a07b9e1fb7a69a6c2d400 Mon Sep 17 00:00:00 2001
From: "mudler's LocalAI [bot]"
 <139863280+localai-bot@users.noreply.github.com>
Date: Mon, 20 Jul 2026 19:34:03 +0200
Subject: [PATCH] gallery: group QAT, APEX and cross-backend builds under their
 base entry (#10983)

feat(gallery): group 21 more model families under variants

Second variant-grouping sweep. QAT and APEX builds are now treated as
quantization techniques rather than distinct weights, per maintainer
ruling, so they group with their base entry instead of standing alone.

Adds 15 new families: quantization and serving-config pairs for
llama-3.2-1b/3b-instruct, dolphin-2.9-llama3-8b, phi-2-chat, ideogram-4,
meta-llama-3.1-8b-instruct, omnivoice-cpp and qwen3-tts-cpp; the gemma-3
4b/12b/27b QAT families; and three cross-backend pairs (silero-vad plus
its sherpa-onnx build, and the vibevoice TTS and ASR builds shared
between the vibevoice-cpp and crispasr backends). The cross-backend
pairs are the first entries that meaningfully exercise engine-preference
ranking during auto-selection.

Restructures four gemma-4 families (31b-it, 26b-a4b-it, e2b-it, e4b-it).
Those bare entries were skipped by the first sweep, which left a QAT
build as parent by default. The bare entry is what installs when nothing
else fits, so it reclaims the parent slot and the former parent becomes
a plain target. Every pre-existing relationship is preserved; nothing is
dropped and nothing nests. gemma-4-12b-it has no bare entry, so it is
left as is.

qwen3-tts-cpp is a YAML anchor with nine merging children, so the five
children that did not already override variants get an explicit empty
list to stop them inheriting the parent's.

Abliterated builds stay excluded: abliteration edits the weights to
remove refusal behaviour, which makes them a different model rather than
another build of the same one.

Assisted-by: Claude:claude-opus-4-8

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
---
 gallery/index.yaml | 54 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 8 deletions(-)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 5b14b927f..848b8d3ad 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1864,8 +1864,6 @@
       sha256: 32f7ea0600c07272547da401d460f8abbd980f3a57b69d6df87be0e2505e0b9c
       uri: https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF/resolve/main/mmproj-F32.gguf
 - name: "gemma-4-26b-a4b-it-qat"
-  variants:
-    - model: gemma-4-26b-a4b-it-qat-q4_0
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF
@@ -1975,8 +1973,6 @@
       uri: https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf/resolve/main/mmproj-gemma-4-12b-it-qat-q4_0.gguf
       sha256: cb018338a7538a9814d994bfe54644c71eb7ed54e31eae2f721e45fd3c260da7
 - name: "gemma-4-e2b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-e2b-it-qat-mtp
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-gguf
@@ -2019,8 +2015,6 @@
       uri: https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-gguf/resolve/main/gemma-4-E2B-it-mmproj.gguf
       sha256: 021059cce659fe7f9170d5599761d7bbaf644b798dab9503aca30dc43e6beb14
 - name: "gemma-4-e4b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-e4b-it-qat-mtp
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf
@@ -2106,8 +2100,6 @@
       uri: https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-gguf/resolve/main/gemma-4-26B-it-mmproj.gguf
       sha256: a359953a076b877db30c31dbbb4c6d93b4a6e017ee5db5784247e4d4c0dd4f3b
 - name: "gemma-4-31b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-31b-it-qat-mtp
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-gguf
@@ -3582,6 +3574,7 @@
   variants:
     - model: qwen3.6-35b-a3b-dflash
     - model: qwen3.6-35b-a3b-nvfp4-mtp
+    - model: qwen3.6-35b-a3b-apex
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF
@@ -3678,6 +3671,10 @@
       sha256: e92ab30c10422ff1863f0d57cf2c206ec3ae47b4903e70c672589dcb7cbec2c6
       uri: https://huggingface.co/mudler/gemma-4-26B-A4B-it-APEX-GGUF/resolve/main/gemma-4-26B-A4B-APEX-Quality.gguf
 - name: gemma-4-26b-a4b-it
+  variants:
+    - model: gemma-4-26b-a4b-it-qat
+    - model: gemma-4-26b-a4b-it-qat-q4_0
+    - model: gemma-4-26b-a4b-it-apex
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/google/gemma-4-26B-A4B-it
@@ -3722,6 +3719,8 @@
 - name: gemma-4-e2b-it
   variants:
     - model: "gemma-4-e2b-it:sglang-mtp"
+    - model: gemma-4-e2b-it-qat-q4_0
+    - model: gemma-4-e2b-it-qat-mtp
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/google/gemma-4-E2B-it
@@ -3767,6 +3766,8 @@
 - name: gemma-4-e4b-it
   variants:
     - model: "gemma-4-e4b-it:sglang-mtp"
+    - model: gemma-4-e4b-it-qat-q4_0
+    - model: gemma-4-e4b-it-qat-mtp
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/google/gemma-4-E4B-it
@@ -3809,6 +3810,9 @@
       sha256: 4c199e460410ba219a8c63930a7121154e1c70cdf66044858f767966332e5a54
       uri: huggingface://ggml-org/gemma-4-E4B-it-GGUF/mmproj-gemma-4-E4B-it-bf16.gguf
 - name: gemma-4-31b-it
+  variants:
+    - model: gemma-4-31b-it-qat-q4_0
+    - model: gemma-4-31b-it-qat-mtp
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/google/gemma-4-31B-it
@@ -6128,6 +6132,8 @@
       sha256: 0599862ac5d15cd308e1d2e368373aea6c02e25ebd1737ad4a4562a0901b0ef8
       uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/vae-BF16.gguf
 - name: vibevoice-cpp
+  variants:
+    - model: vibevoice-tts-crispasr
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/mudler/vibevoice.cpp-models
@@ -6174,6 +6180,8 @@
       sha256: b15cd8b9cae6ee2c3d20b0ee6e7bfe93f13489f8b63b6834e9bbf0dfabf6505a
       uri: huggingface://mudler/vibevoice.cpp-models/voice-en-Carter_man.gguf
 - name: vibevoice-cpp-asr
+  variants:
+    - model: vibevoice-crispasr
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/mudler/vibevoice.cpp-models
@@ -6217,6 +6225,8 @@
       uri: huggingface://mudler/vibevoice.cpp-models/tokenizer.gguf
 - &qwenttscpp_gallery
   name: qwen3-tts-cpp
+  variants:
+    - model: qwen3-tts-cpp-0.6b-base-q4
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/Serveurperso/Qwen3-TTS-GGUF
@@ -6252,6 +6262,7 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-0.6b-base-q4
+  variants: []
   description: |
     Qwen3-TTS 0.6B Base (C++ / GGML, qwentts.cpp), Q4_K_M (~0.6 GB talker).
     Streaming + voice cloning, 24kHz mono, 11 languages.
@@ -6292,6 +6303,7 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-base-q4
+  variants: []
   description: |
     Qwen3-TTS 1.7B Base (C++ / GGML, qwentts.cpp), Q4_K_M (~1.2 GB talker).
     Streaming + voice cloning, 24kHz mono, 11 languages.
@@ -6342,6 +6354,7 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-customvoice-q4
+  variants: []
   description: |
     Qwen3-TTS 0.6B CustomVoice (C++ / GGML, qwentts.cpp), Q4_K_M. Named speakers
     via the `voice` field (serena, vivian, ryan, aiden, eric, dylan, ...).
@@ -6400,6 +6413,7 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-customvoice-q4
+  variants: []
   description: |
     Qwen3-TTS 1.7B CustomVoice (C++ / GGML, qwentts.cpp), Q4_K_M. Named speakers
     via the `voice` field. Streaming, 24kHz mono, 11 languages.
@@ -6458,6 +6472,7 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-voicedesign-q4
+  variants: []
   description: |
     Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q4_K_M. Synthesises a
     speaker from a free-text attribute instruction - REQUIRES the `instructions`
@@ -6551,6 +6566,8 @@
       sha256: d0f4f371f80ff32ba222b1b39c192df8285c7b88986a55f954454db69618479e
       uri: huggingface://mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF/moss-tokenizer-v1_5.gguf
 - name: omnivoice-cpp
+  variants:
+    - model: omnivoice-cpp-hq
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/Serveurperso/OmniVoice-GGUF
@@ -15481,6 +15498,9 @@
       sha256: fadc3e5f8d42bf7e894a785b05082e47daee4df26680389817e2093056f088ad
       uri: huggingface://unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
 - name: gemma-3-27b-it
+  variants:
+    - model: gemma-3-27b-it-qat
+    - model: google-gemma-3-27b-it-qat-q4_0-small
   url: github:mudler/LocalAI/gallery/gemma.yaml@master
   urls:
     - https://ai.google.dev/gemma/docs
@@ -15512,6 +15532,8 @@
       sha256: 54cb61c842fe49ac3c89bc1a614a2778163eb49f3dec2b90ff688b4c0392cb48
       uri: huggingface://lmstudio-community/gemma-3-27b-it-GGUF/mmproj-model-f16.gguf
 - name: gemma-3-12b-it
+  variants:
+    - model: gemma-3-12b-it-qat
   url: github:mudler/LocalAI/gallery/gemma.yaml@master
   urls:
     - https://ai.google.dev/gemma/docs/core
@@ -15543,6 +15565,8 @@
       sha256: 30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5
       uri: huggingface://lmstudio-community/gemma-3-12b-it-GGUF/mmproj-model-f16.gguf
 - name: gemma-3-4b-it
+  variants:
+    - model: gemma-3-4b-it-qat
   url: github:mudler/LocalAI/gallery/gemma.yaml@master
   urls:
     - https://ai.google.dev/gemma/docs/core
@@ -19541,6 +19565,8 @@
       sha256: 555b91485955bc96eb445b57dd4bbf8809aa7d8cce7c313f4f8bc5b2340896b4
       uri: huggingface://bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf
 - name: llama-3.2-1b-instruct:q4_k_m
+  variants:
+    - model: "llama-3.2-1b-instruct:q8_0"
   url: github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master
   urls:
     - https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
@@ -19571,6 +19597,8 @@
       sha256: 1d0e9419ec4e12aef73ccf4ffd122703e94c48344a96bc7c5f0f2772c2152ce3
       uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
 - name: llama-3.2-3b-instruct:q4_k_m
+  variants:
+    - model: "llama-3.2-3b-instruct:q8_0"
   url: github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master
   urls:
     - https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF
@@ -20981,6 +21009,9 @@
       sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
       uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf
 - name: meta-llama-3.1-8b-instruct
+  variants:
+    - model: "meta-llama-3.1-8b-instruct:grammar-functioncall"
+    - model: "meta-llama-3.1-8b-instruct:Q8_grammar-functioncall"
   url: github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master
   urls:
     - https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
@@ -29364,6 +29395,8 @@
       sha256: 236fcf372bb25f314dafa1605d84566db60ddad98b889aaa072a3108ec48ef22
       uri: huggingface://mradermacher/Arch-Router-1.5B-GGUF/Arch-Router-1.5B.Q8_0.gguf
 - name: dolphin-2.9-llama3-8b
+  variants:
+    - model: "dolphin-2.9-llama3-8b:Q6_K"
   url: github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master
   urls:
     - https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-gguf
@@ -29979,6 +30012,8 @@
       sha256: 0cf542a127c2c835066a78028009b7eddbaf773cc2a26e1cb157ce5e09c1a2e0
       uri: huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf
 - name: phi-2-chat
+  variants:
+    - model: "phi-2-chat:Q8_0"
   url: github:mudler/LocalAI/gallery/phi-2-chat.yaml@master
   urls:
     - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml
@@ -31425,6 +31460,8 @@
       sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
       uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
 - name: ideogram-4-iq4nl-ggml
+  variants:
+    - model: ideogram-4-q8_0-ggml
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/ideogram-ai/ideogram-4-fp8
@@ -35318,6 +35355,7 @@
 - name: silero-vad
   variants:
     - model: silero-vad-ggml
+    - model: silero-vad-sherpa
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/snakers4/silero-vad