diff --git a/gallery/index.yaml b/gallery/index.yaml
index a91089bfb..3aeb87806 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -120,6 +120,9 @@
       uri: huggingface://prism-ml/Bonsai-8B-gguf/Bonsai-8B-Q1_0.gguf
 - &ternary-bonsai-8b
   name: "ternary-bonsai-8b"
+  variants:
+    - model: ternary-bonsai-8b-q2-g64
+    - model: ternary-bonsai-8b-pq2
   url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
   license: apache-2.0
   icon: https://huggingface.co/prism-ml/Ternary-Bonsai-8B-gguf/resolve/main/assets/bonsai-logo.svg
@@ -156,6 +159,7 @@
       uri: huggingface://prism-ml/Ternary-Bonsai-8B-gguf/Ternary-Bonsai-8B-Q2_0.gguf
 - !!merge <<: *ternary-bonsai-8b
   name: "ternary-bonsai-8b-q2-g64"
+  variants: []
   description: |
     Ternary Bonsai 8B (PrismML), GGUF Q2_0 with group-64 packing (each FP16 scale shared
     across 64 weights instead of 128). Slightly larger (~2.31 GB) but matches llama.cpp's
@@ -173,6 +177,7 @@
       uri: huggingface://prism-ml/Ternary-Bonsai-8B-gguf/Ternary-Bonsai-8B-Q2_0_g64.gguf
 - !!merge <<: *ternary-bonsai-8b
   name: "ternary-bonsai-8b-pq2"
+  variants: []
   description: |
     Ternary Bonsai 8B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~2.18 GB).
     Same {-1, 0, +1} weight alphabet as Q2_0. Runs on LocalAI's `bonsai` backend.
@@ -232,6 +237,9 @@
       uri: huggingface://prism-ml/Bonsai-27B-gguf/Bonsai-27B-mmproj-Q8_0.gguf
 - &ternary-bonsai-27b
   name: "ternary-bonsai-27b"
+  variants:
+    - model: ternary-bonsai-27b-pq2
+    - model: ternary-bonsai-27b-q2-g64
   url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
   license: apache-2.0
   icon: https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf/resolve/main/assets/bonsai-logo.svg
@@ -274,6 +282,7 @@
       uri: huggingface://prism-ml/Ternary-Bonsai-27B-gguf/Ternary-Bonsai-27B-mmproj-Q8_0.gguf
 - !!merge <<: *ternary-bonsai-27b
   name: "ternary-bonsai-27b-pq2"
+  variants: []
   description: |
     Ternary Bonsai 27B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~7.17 GB) with
     the 4-bit vision tower (mmproj) included. Runs on LocalAI's `bonsai` backend.
@@ -295,6 +304,7 @@
       uri: huggingface://prism-ml/Ternary-Bonsai-27B-gguf/Ternary-Bonsai-27B-mmproj-Q8_0.gguf
 - !!merge <<: *ternary-bonsai-27b
   name: "ternary-bonsai-27b-q2-g64"
+  variants: []
   description: |
     Ternary Bonsai 27B (PrismML), GGUF Q2_0 with group-64 packing (~7.59 GB), matching
     llama.cpp's native 64-value Q2_0 block layout, with the 4-bit vision tower (mmproj)
@@ -372,6 +382,10 @@
       uri: https://huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF/resolve/main/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q4_K_M.gguf
       sha256: b1c3bf2995e96cb792a0031e4e1497a500e9244c68ba17c24a7e6edf1fc59019
 - name: "deepseek-v4-flash"
+  variants:
+    - model: deepseek-v4-flash-q2
+    - model: deepseek-v4-flash-q2-q4
+    - model: deepseek-v4-flash-q4-ssd
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF
@@ -1686,6 +1700,8 @@
       sha256: 88956c71d20444d3ebf890e4495afed3257c6be877d4e82f0c26ce58e79b340f
       uri: https://huggingface.co/ReadyArt/Dark-Scarlett-v0.3-26B-A4B-GGUF/resolve/main/Dark-Scarlett-v0.3-26B-A4B-Q4_K_M.gguf
 - name: "qwopus3.6-27b-coder-mtp"
+  variants:
+    - model: qwopus3.6-27b-coder-mtp-nvfp4
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
@@ -1723,6 +1739,8 @@
       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
@@ -2337,6 +2355,8 @@
       sha256: 01b76572f80b7d2ebee80a27cb9c3699c26b04cae1c402eee7664fc17a4b5ce6
       uri: https://huggingface.co/LocalAI-io/privacy-filter-multilingual-GGUF/resolve/main/privacy-filter-multilingual-f16.gguf
 - name: "privacy-filter-nemotron"
+  variants:
+    - model: privacy-filter-nemotron-q8
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png
   urls:
@@ -2540,6 +2560,8 @@
       sha256: f48daca405a1c768a9514e392c3955dcc4a9d66a5cf64cf45e064092b5f20ee4
       uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-mmproj.gguf
 - name: "qwopus3.6-27b-v2-mtp"
+  variants:
+    - model: qwopus3.6-27b-v2-mtp-nvfp4
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
     - https://huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF
@@ -4442,6 +4464,8 @@
       sha256: 5c058d9f7b737167195fa54eae4a2ae17658ac2c0a8073f7f116ba006b2ab32c
       uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-base-f16.gguf
 - name: ced-base-q8
+  variants:
+    - model: ced-base-f16
   url: github:mudler/LocalAI/gallery/ced.yaml@master
   urls:
     - https://huggingface.co/mudler/ced-gguf
@@ -4488,6 +4512,8 @@
       sha256: af8b81c67bae50bfca4ea83dbba77b3bae4fa6180d36c17d6877f7700aeeb77b
       uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-tiny-f16.gguf
 - name: ced-tiny-q8
+  variants:
+    - model: ced-tiny-f16
   url: github:mudler/LocalAI/gallery/ced.yaml@master
   urls:
     - https://huggingface.co/mudler/ced-gguf
@@ -4534,6 +4560,8 @@
       sha256: 3c6a8936c77312f07a9ecb7b4bbbcb1f93ad137920ca6656bae9306571fb0c03
       uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-mini-f16.gguf
 - name: ced-mini-q8
+  variants:
+    - model: ced-mini-f16
   url: github:mudler/LocalAI/gallery/ced.yaml@master
   urls:
     - https://huggingface.co/mudler/ced-gguf
@@ -4580,6 +4608,8 @@
       sha256: c391ed8697a1b08d7c1a463e4940a5c3a2f670e0544ab0d8ee23b544583602a8
       uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-small-f16.gguf
 - name: ced-small-q8
+  variants:
+    - model: ced-small-f16
   url: github:mudler/LocalAI/gallery/ced.yaml@master
   urls:
     - https://huggingface.co/mudler/ced-gguf
@@ -6056,6 +6086,8 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-base
+  variants:
+    - model: qwen3-tts-cpp-1.7b-base-q4
   description: |
     Qwen3-TTS 1.7B Base (C++ / GGML, qwentts.cpp), Q8_0 (~2.0 GB talker).
     Higher-quality streaming + voice cloning, 24kHz mono, 11 languages.
@@ -6094,6 +6126,8 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-customvoice
+  variants:
+    - model: qwen3-tts-cpp-customvoice-q4
   description: |
     Qwen3-TTS 0.6B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers
     selected via the `voice` field: serena, vivian, uncle_fu, ryan, aiden,
@@ -6151,6 +6185,8 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-customvoice
+  variants:
+    - model: qwen3-tts-cpp-1.7b-customvoice-q4
   description: |
     Qwen3-TTS 1.7B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers via
     the `voice` field (serena, vivian, ryan, aiden, eric, dylan, ...). Streaming,
@@ -6206,6 +6242,8 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
 - !!merge <<: *qwenttscpp_gallery
   name: qwen3-tts-cpp-1.7b-voicedesign
+  variants:
+    - model: qwen3-tts-cpp-1.7b-voicedesign-q4
   description: |
     Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q8_0. Synthesises a
     speaker from a free-text attribute instruction - REQUIRES the OpenAI
@@ -6263,6 +6301,8 @@
       uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
 - &mossttscpp_gallery
   name: moss-tts-cpp-v1_5-q8_0
+  variants:
+    - model: moss-tts-cpp-v1_5-f16
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF
@@ -6304,6 +6344,7 @@
       uri: huggingface://mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF/moss-tokenizer-v1_5.gguf
 - !!merge <<: *mossttscpp_gallery
   name: moss-tts-cpp-v1_5-f16
+  variants: []
   description: |
     MOSS-TTS-Local v1.5 (C++/ggml, moss-tts.cpp), F16 (~9.4 GB), code-exact versus the
     reference. 48kHz stereo text-to-speech with reference-audio voice cloning.
@@ -8019,6 +8060,8 @@
       sha256: cd5a851d3928697fa1bd76d459d2cc409b6cf40c9d9682b2f5c8e7c6a9f9630f
       uri: huggingface://unsloth/Qwen3-VL-2B-Instruct-GGUF/mmproj-F16.gguf
 - name: huihui-qwen3-vl-30b-a3b-instruct-abliterated
+  variants:
+    - model: huihui-qwen3-vl-30b-a3b-instruct-abliterated-mxfp4_moe
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/noctrex/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF
@@ -8538,6 +8581,8 @@
       sha256: c5c38bfa5d8d5100e91a2e0050a0b2f3e082cd4bfd423cb527abc3b6f1ae180c
       uri: huggingface://bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf
 - name: opengvlab_internvl3_5-30b-a3b
+  variants:
+    - model: opengvlab_internvl3_5-30b-a3b-q8_0
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B
@@ -8635,6 +8680,8 @@
       sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d
       uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf
 - name: opengvlab_internvl3_5-14b
+  variants:
+    - model: opengvlab_internvl3_5-14b-q8_0
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/OpenGVLab/InternVL3_5-14B
@@ -8667,6 +8714,8 @@
       sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d
       uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf
 - name: opengvlab_internvl3_5-8b
+  variants:
+    - model: opengvlab_internvl3_5-8b-q8_0
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/OpenGVLab/InternVL3_5-8B
@@ -8729,6 +8778,8 @@
       sha256: 212cc090f81ea2981b870186d4b424fae69489a5313a14e52ffdb2e877852389
       uri: huggingface://bartowski/OpenGVLab_InternVL3_5-8B-GGUF/mmproj-OpenGVLab_InternVL3_5-8B-f16.gguf
 - name: opengvlab_internvl3_5-4b
+  variants:
+    - model: opengvlab_internvl3_5-4b-q8_0
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/OpenGVLab/InternVL3_5-4B
@@ -9956,6 +10007,8 @@
       sha256: ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676
       uri: https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx
 - name: insightface-opencv
+  variants:
+    - model: insightface-opencv-int8
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/opencv/opencv_zoo
@@ -10649,6 +10702,10 @@
       sha256: 0909d8a1aba584b482d501baae032611d1559878be1b7f6606ba516687c5380d
 - &depth-anything-3-base
   name: depth-anything-3-base
+  variants:
+    - model: depth-anything-3-base-q8_0
+    - model: depth-anything-3-base-f16
+    - model: depth-anything-3-base-f32
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/mudler/depth-anything.cpp
@@ -10680,6 +10737,7 @@
       sha256: "43cd45d00f9024f4319f4beabd73155db5132e4b575bc52eff4131262c9d78f1"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-base-q8_0
+  variants: []
   description: |
     Depth Anything 3 (base), q8_0 — near-lossless 8-bit quant (~149 MB). Same
     depth + camera pose output as the q4_k default at higher fidelity.
@@ -10693,6 +10751,7 @@
       sha256: "71b1c953113657f9a4fbef43ab6a16fe7a6f87b36da113a184f13c4a564968a0"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-base-f16
+  variants: []
   description: |
     Depth Anything 3 (base), f16 — half precision (~233 MB), no measurable
     accuracy loss vs f32. Depth + camera pose.
@@ -10706,6 +10765,7 @@
       sha256: "2975419c99702ca646d5b7120c53e35c9fee158f0a803577241d16957f75624b"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-base-f32
+  variants: []
   description: |
     Depth Anything 3 (base), f32 — maximum fidelity (~412 MB). Reference-parity
     depth + camera pose.
@@ -10719,6 +10779,7 @@
       sha256: "1b13b166e8a8b4f2c862f42d36edb2f9aab995a18cc527a52b9f160b99c6b8da"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-giant
+  variants: []
   description: |
     Depth Anything 3 (giant / vitg), f32 — the large backbone (~4.9 GB) for
     maximum quality depth + camera pose. GPU recommended.
@@ -10739,6 +10800,7 @@
       sha256: "392edf64626be6a985487beb39c8d54cdc14f7feb2b53323742c96b71e7e7181"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-small
+  variants: []
   description: |
     Depth Anything 3 (small / vits), f32 — the smallest backbone (~131 MB) for
     fast CPU depth + camera pose. Same output as base at lower latency.
@@ -10752,6 +10814,7 @@
       sha256: "eab5597e01dedde1a20c038590ae8c887b85ec35b882581138c08308e92c41e5"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-large
+  variants: []
   description: |
     Depth Anything 3 (large / vitl), f32 (~1.6 GB) — higher quality depth +
     camera pose than base. GPU recommended for interactive use.
@@ -10772,6 +10835,7 @@
       sha256: "a79eb3e19e8ec49f4daac484fb5fb67e15baac61518d229cf819e40c87080906"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-mono-large
+  variants: []
   description: |
     Depth Anything 3 (monocular large / vitl), f32 (~1.3 GB) — single-image
     monocular depth + a sky mask (no camera pose). DPT single-head variant; use
@@ -10786,6 +10850,7 @@
       sha256: "291b1a554af907c3f79986ee225da8933be5f7a31d73c81d06784cda284535de"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-metric-large
+  variants: []
   description: |
     Depth Anything 3 (metric large / vitl), f32 (~1.3 GB) — single-image
     metric-scale depth (meters) + a sky mask. DPT single-head metric variant; use
@@ -10801,6 +10866,7 @@
       sha256: "d10b7450c2238244b2d72e2749537a1876255180149cd630a18bc1619c9286be"
 - !!merge <<: *depth-anything-3-base
   name: depth-anything-3-nested
+  variants: []
   description: |
     Depth Anything 3 (nested giant+large), f32 — the recommended metric model. A
     two-branch pipeline: the anyview GIANT (vitg) branch and a metric ViT-L branch
@@ -10832,6 +10898,10 @@
       sha256: "b54ed50cbc0b0c14fae1f8edd0fea8bd1cac0850485fd6e7eb2422c7a19e570e"
 - &depth-anything-2-base
   name: depth-anything-2-base
+  variants:
+    - model: depth-anything-2-base-q8_0
+    - model: depth-anything-2-base-f16
+    - model: depth-anything-2-base-f32
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/mudler/depth-anything.cpp
@@ -10862,6 +10932,7 @@
       sha256: "49e77ec7e593080111242fa76017cae3e26498d550841cf8a70dfcd36bb175f2"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-base-q8_0
+  variants: []
   description: |
     Depth Anything V2 (base / ViT-B), q8_0 — near-lossless 8-bit quant. Same
     relative monocular depth output as the q4_k default at higher fidelity. Use
@@ -10876,6 +10947,7 @@
       sha256: "11920ec7a8dfc2fa7fe8ed44811a46fafe415c641d13144bb733d1437832291b"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-base-f16
+  variants: []
   description: |
     Depth Anything V2 (base / ViT-B), f16 — half precision, no measurable
     accuracy loss vs f32. Relative monocular depth only (no pose). Use
@@ -10890,6 +10962,7 @@
       sha256: "e91c011fbbf90a44639fea55b8d61ca9e80dfb5541220946c8b6e6261fe67ab1"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-base-f32
+  variants: []
   description: |
     Depth Anything V2 (base / ViT-B), f32 — maximum reference fidelity. Relative
     monocular depth only (no pose). Use GenerateImage (src -> depth PNG) or the
@@ -10904,6 +10977,7 @@
       sha256: "2d3d2e4d8fae9646c17577b84c870c7d77a34ded8cf8d5da0a60b2bee1530ccc"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-small
+  variants: []
   description: |
     Depth Anything V2 (small / ViT-S), f32 — the smallest, fastest backbone for
     relative monocular depth on CPU. Depth only (no pose). Use GenerateImage
@@ -10918,6 +10992,7 @@
       sha256: "1f6622aa70cbd0eba34d34e2f635a156ed8c3f8e158fb149eb355366e2deb899"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-large
+  variants: []
   description: |
     Depth Anything V2 (large / ViT-L), f32 — higher-quality relative monocular
     depth than base. Depth only (no pose). Use GenerateImage (src -> depth PNG)
@@ -10932,6 +11007,7 @@
       sha256: "e187658b01b6df62e1553b03df9973606a7287551d4771b09802fc10b26f19f3"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-hypersim-small
+  variants: []
   description: |
     Depth Anything V2 Metric (Hypersim, indoor / ViT-S), q4_k — metric monocular
     depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
@@ -10953,6 +11029,7 @@
       sha256: "decd99f5c756b564aae5ca1a1612f896e7f76889060e1d25ba610549bbc39b52"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-hypersim-base
+  variants: []
   description: |
     Depth Anything V2 Metric (Hypersim, indoor / ViT-B), q4_k — metric monocular
     depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
@@ -10974,6 +11051,7 @@
       sha256: "c7c6a8628ac154f2ad43db09b8146518e863375be2cb03b8b46caec49a4fcf3a"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-hypersim-large
+  variants: []
   description: |
     Depth Anything V2 Metric (Hypersim, indoor / ViT-L), q4_k — highest-quality
     metric monocular depth in METRES (indoor, max_depth 20). Depth only (no
@@ -10995,6 +11073,7 @@
       sha256: "3664506bea55e64926fff2cb112ea5a9ad923d13647b9c69617184a89dd1e473"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-vkitti-small
+  variants: []
   description: |
     Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-S), q4_k — metric
     monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
@@ -11016,6 +11095,7 @@
       sha256: "8dcaa5d0f8475c3dc5de59e28faacd6d46e5ef73c73ecc58e365d7751bc2279f"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-vkitti-base
+  variants: []
   description: |
     Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-B), q4_k — metric
     monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
@@ -11037,6 +11117,7 @@
       sha256: "1de5a7aae674df6afb8fa5e06d67843dccfbab92cd64b7c816c1218229446d6d"
 - !!merge <<: *depth-anything-2-base
   name: depth-anything-2-metric-vkitti-large
+  variants: []
   description: |
     Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-L), q4_k —
     highest-quality metric monocular depth in METRES (outdoor, max_depth 80).
@@ -29035,6 +29116,8 @@
 - &arch-router-1_5b
   url: github:mudler/LocalAI/gallery/chatml.yaml@master
   name: arch-router-1.5b-q4
+  variants:
+    - model: arch-router-1.5b-q8
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/66b681906c8d3b36786b764c/uyP7mxDVv0HbV9Hv_KfHk.jpeg
   license: other
   urls:
@@ -29080,6 +29163,7 @@
       uri: huggingface://mradermacher/Arch-Router-1.5B-GGUF/Arch-Router-1.5B.Q4_K_M.gguf
 - !!merge <<: *arch-router-1_5b
   name: arch-router-1.5b-q8
+  variants: []
   overrides:
     known_usecases:
       - score
@@ -30660,6 +30744,9 @@
       sha256: f4df16c641a05c4a6ca717068ba3ee312875000f6fac0efbd152915553b5fc3e
       uri: huggingface://second-state/stable-diffusion-3.5-large-GGUF/t5xxl-Q5_0.gguf
 - name: flux.1-dev
+  variants:
+    - model: flux.1-dev-ggml
+    - model: flux.1-dev-ggml-q8_0
   url: github:mudler/LocalAI/gallery/flux.yaml@master
   urls:
     - https://huggingface.co/black-forest-labs/FLUX.1-dev
@@ -30909,6 +30996,8 @@
       sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
       uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
 - name: flux.1-krea-dev-ggml
+  variants:
+    - model: flux.1-krea-dev-ggml-q8_0
   url: github:mudler/LocalAI/gallery/flux-ggml.yaml@master
   urls:
     - https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev
@@ -31302,6 +31391,8 @@
       sha256: 422f1ae452ade6f30a004d7e5c6a43195e4433bc370bf23fac9cc591f01a8898
       uri: huggingface://ggerganov/whisper.cpp/ggml-base-q5_1.bin
 - name: whisper-base
+  variants:
+    - model: whisper-base-q5_1
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31356,6 +31447,8 @@
       sha256: 4baf70dd0d7c4247ba2b81fafd9c01005ac77c2f9ef064e00dcf195d0e2fdd2f
       uri: huggingface://ggerganov/whisper.cpp/ggml-base.en-q5_1.bin
 - name: whisper-base-en
+  variants:
+    - model: whisper-base-en-q5_1
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31410,6 +31503,8 @@
       sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1
       uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin
 - name: whisper-medium
+  variants:
+    - model: whisper-medium-q5_0
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31490,6 +31585,8 @@
       sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb
       uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin
 - name: whisper-small
+  variants:
+    - model: whisper-small-q5_1
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31544,6 +31641,8 @@
       sha256: bfdff4894dcb76bbf647d56263ea2a96645423f1669176f4844a1bf8e478ad30
       uri: huggingface://ggerganov/whisper.cpp/ggml-small.en-q5_1.bin
 - name: whisper-small-en
+  variants:
+    - model: whisper-small-en-q5_1
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31598,6 +31697,8 @@
       sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb
       uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin
 - name: whisper-tiny
+  variants:
+    - model: whisper-tiny-q5_1
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31677,6 +31778,9 @@
       sha256: c77c5766f1cef09b6b7d47f21b546cbddd4157886b3b5d6d4f709e91e66c7c2b
       uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q5_1.bin
 - name: whisper-tiny-en
+  variants:
+    - model: whisper-tiny-en-q5_1
+    - model: whisper-tiny-en-q8_0
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31728,6 +31832,8 @@
       sha256: 5bc2b3860aa151a4c6e7bb095e1fcce7cf12c7b020ca08dcec0c6d018bb7dd94
       uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q8_0.bin
 - name: whisper-large
+  variants:
+    - model: whisper-large-q5_0
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -31781,6 +31887,9 @@
       sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1
       uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin
 - name: whisper-large-turbo
+  variants:
+    - model: whisper-large-turbo-q5_0
+    - model: whisper-large-turbo-q8_0
   url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
   urls:
     - https://github.com/ggerganov/whisper.cpp
@@ -35020,6 +35129,8 @@
       sha256: af8cb9e4ca0bf19eb54d08c612fdf325059264abbbd2c619527e5d2dda8de655
       uri: https://huggingface.co/mradermacher/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.f16.gguf
 - name: silero-vad
+  variants:
+    - model: silero-vad-ggml
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/snakers4/silero-vad
@@ -36314,6 +36425,8 @@
       sha256: 0a599099e93ad521045e17d82365a73c1738fff0603d6cb2c9557e96fbc907cb
       uri: huggingface://mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF/YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
 - name: orca-agent-v0.1
+  variants:
+    - model: orca-agent-v0.1-i1
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls:
     - https://huggingface.co/mradermacher/Orca-Agent-v0.1-GGUF
@@ -36539,6 +36652,9 @@
       uri: huggingface://unsloth/LTX-2.3-GGUF/text_encoders/ltx-2.3-22b-dev_embeddings_connectors.safetensors
 - !!merge <<: *ltx-2-3-dev-ggml
   name: ltx-2.3-22b-dev-ggml-q4_k_m
+  variants:
+    - model: ltx-2.3-22b-dev-ggml
+    - model: ltx-2.3-22b-dev-ggml-q8_0
   description: |
     LTX-2.3 22B dev - non-dynamic Q4_K_M quantization (~14.3 GB). Same
     pipeline as ltx-2.3-22b-dev-ggml but with the plain Q4_K_M weights
@@ -36666,6 +36782,9 @@
       uri: huggingface://unsloth/LTX-2.3-GGUF/text_encoders/ltx-2.3-22b-distilled_embeddings_connectors.safetensors
 - !!merge <<: *ltx-2-3-distilled-ggml
   name: ltx-2.3-22b-distilled-ggml-q4_k_m
+  variants:
+    - model: ltx-2.3-22b-distilled-ggml
+    - model: ltx-2.3-22b-distilled-ggml-q8_0
   description: |
     LTX-2.3 22B distilled - non-dynamic Q4_K_M quantization (~14.3 GB).
     Same pipeline as ltx-2.3-22b-distilled-ggml but with the plain Q4_K_M