mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 09:57:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

gallery: group alternative builds of the same weights under variants

Browse Source 
Sweep the gallery for entries that are alternative builds of the same
weights (different quantization, precision, or runtime format) and declare
them as variants of a single parent row, so the listing offers one row per
model instead of one row per quantization and the installer picks the
largest build that this host can actually run.

41 families over 95 entries, turning 54 entries into variants.

The parent is the bare-named entry wherever one exists, so nothing changes
about what any existing entry installs. Ranking already selects the largest
fitting build regardless of which entry is nominally the parent, so the
parent only decides the pathological case where nothing fits. For the ten
families that have no bare-named entry, the smallest build is the parent,
since that is the one that has to install when nothing fits.

Grouping was verified against the actual model filenames rather than the
entry names alone. Different parameter sizes, languages, finetunes, and
products that merely share a name prefix are left as separate rows: the
qwen3.6 APEX and pi-tune finetunes, the DFlash and MTP speculative-decoding
pairings, English-only versus multilingual Whisper, the QAT versus non-QAT
Gemma 4 weights, and the abliterated FLUX build are all distinct models.

Six parents define YAML anchors that other entries pull in with a merge key,
which would have handed their variants to every merging child. For the two
depth-anything anchors that would have made fourteen unrelated entries
advertise the base model's builds as their own. All 26 merging children
therefore carry an explicit empty variants list, which overrides the merged
key and is equivalent to the key being absent.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2026-07-19 21:15:00 +00:00
parent dd20e8f486
commit 29c49203b7
1 changed files with 119 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
gallery/index.yaml
View File

@@ -120,6 +120,9 @@
uri: huggingface://prism-ml/Bonsai-8B-gguf/Bonsai-8B-Q1_0.gguf uri: huggingface://prism-ml/Bonsai-8B-gguf/Bonsai-8B-Q1_0.gguf
- &ternary-bonsai-8b - &ternary-bonsai-8b
name: "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" url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
license: apache-2.0 license: apache-2.0
icon: https://huggingface.co/prism-ml/Ternary-Bonsai-8B-gguf/resolve/main/assets/bonsai-logo.svg 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 uri: huggingface://prism-ml/Ternary-Bonsai-8B-gguf/Ternary-Bonsai-8B-Q2_0.gguf
- !!merge <<: *ternary-bonsai-8b - !!merge <<: *ternary-bonsai-8b
name: "ternary-bonsai-8b-q2-g64" name: "ternary-bonsai-8b-q2-g64"
variants: []
description: | description: |
Ternary Bonsai 8B (PrismML), GGUF Q2_0 with group-64 packing (each FP16 scale shared 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 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 uri: huggingface://prism-ml/Ternary-Bonsai-8B-gguf/Ternary-Bonsai-8B-Q2_0_g64.gguf
- !!merge <<: *ternary-bonsai-8b - !!merge <<: *ternary-bonsai-8b
name: "ternary-bonsai-8b-pq2" name: "ternary-bonsai-8b-pq2"
variants: []
description: | description: |
Ternary Bonsai 8B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~2.18 GB). 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. 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 uri: huggingface://prism-ml/Bonsai-27B-gguf/Bonsai-27B-mmproj-Q8_0.gguf
- &ternary-bonsai-27b - &ternary-bonsai-27b
name: "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" url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
license: apache-2.0 license: apache-2.0
icon: https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf/resolve/main/assets/bonsai-logo.svg 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 uri: huggingface://prism-ml/Ternary-Bonsai-27B-gguf/Ternary-Bonsai-27B-mmproj-Q8_0.gguf
- !!merge <<: *ternary-bonsai-27b - !!merge <<: *ternary-bonsai-27b
name: "ternary-bonsai-27b-pq2" name: "ternary-bonsai-27b-pq2"
variants: []
description: | description: |
Ternary Bonsai 27B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~7.17 GB) with 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. 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 uri: huggingface://prism-ml/Ternary-Bonsai-27B-gguf/Ternary-Bonsai-27B-mmproj-Q8_0.gguf
- !!merge <<: *ternary-bonsai-27b - !!merge <<: *ternary-bonsai-27b
name: "ternary-bonsai-27b-q2-g64" name: "ternary-bonsai-27b-q2-g64"
variants: []
description: | description: |
Ternary Bonsai 27B (PrismML), GGUF Q2_0 with group-64 packing (~7.59 GB), matching 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) 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 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 sha256: b1c3bf2995e96cb792a0031e4e1497a500e9244c68ba17c24a7e6edf1fc59019
- name: "deepseek-v4-flash" - 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" url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: urls:
- https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF - https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF
@@ -1686,6 +1700,8 @@
sha256: 88956c71d20444d3ebf890e4495afed3257c6be877d4e82f0c26ce58e79b340f 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 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" - name: "qwopus3.6-27b-coder-mtp"
variants:
- model: qwopus3.6-27b-coder-mtp-nvfp4
url: "github:mudler/LocalAI/gallery/virtual.yaml@master" url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: urls:
- https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF - https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
@@ -1723,6 +1739,8 @@
sha256: 32f7ea0600c07272547da401d460f8abbd980f3a57b69d6df87be0e2505e0b9c sha256: 32f7ea0600c07272547da401d460f8abbd980f3a57b69d6df87be0e2505e0b9c
uri: https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF/resolve/main/mmproj-F32.gguf uri: https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF/resolve/main/mmproj-F32.gguf
- name: "gemma-4-26b-a4b-it-qat" - 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" url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: urls:
- https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF - https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF
@@ -2337,6 +2355,8 @@
sha256: 01b76572f80b7d2ebee80a27cb9c3699c26b04cae1c402eee7664fc17a4b5ce6 sha256: 01b76572f80b7d2ebee80a27cb9c3699c26b04cae1c402eee7664fc17a4b5ce6
uri: https://huggingface.co/LocalAI-io/privacy-filter-multilingual-GGUF/resolve/main/privacy-filter-multilingual-f16.gguf uri: https://huggingface.co/LocalAI-io/privacy-filter-multilingual-GGUF/resolve/main/privacy-filter-multilingual-f16.gguf
- name: "privacy-filter-nemotron" - name: "privacy-filter-nemotron"
variants:
- model: privacy-filter-nemotron-q8
url: "github:mudler/LocalAI/gallery/virtual.yaml@master" url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png
urls: urls:
@@ -2540,6 +2560,8 @@
sha256: f48daca405a1c768a9514e392c3955dcc4a9d66a5cf64cf45e064092b5f20ee4 sha256: f48daca405a1c768a9514e392c3955dcc4a9d66a5cf64cf45e064092b5f20ee4
uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-mmproj.gguf 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" - name: "qwopus3.6-27b-v2-mtp"
variants:
- model: qwopus3.6-27b-v2-mtp-nvfp4
url: "github:mudler/LocalAI/gallery/virtual.yaml@master" url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: urls:
- https://huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF - https://huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF
@@ -4442,6 +4464,8 @@
sha256: 5c058d9f7b737167195fa54eae4a2ae17658ac2c0a8073f7f116ba006b2ab32c sha256: 5c058d9f7b737167195fa54eae4a2ae17658ac2c0a8073f7f116ba006b2ab32c
uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-base-f16.gguf uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-base-f16.gguf
- name: ced-base-q8 - name: ced-base-q8
variants:
- model: ced-base-f16
url: github:mudler/LocalAI/gallery/ced.yaml@master url: github:mudler/LocalAI/gallery/ced.yaml@master
urls: urls:
- https://huggingface.co/mudler/ced-gguf - https://huggingface.co/mudler/ced-gguf
@@ -4488,6 +4512,8 @@
sha256: af8b81c67bae50bfca4ea83dbba77b3bae4fa6180d36c17d6877f7700aeeb77b sha256: af8b81c67bae50bfca4ea83dbba77b3bae4fa6180d36c17d6877f7700aeeb77b
uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-tiny-f16.gguf uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-tiny-f16.gguf
- name: ced-tiny-q8 - name: ced-tiny-q8
variants:
- model: ced-tiny-f16
url: github:mudler/LocalAI/gallery/ced.yaml@master url: github:mudler/LocalAI/gallery/ced.yaml@master
urls: urls:
- https://huggingface.co/mudler/ced-gguf - https://huggingface.co/mudler/ced-gguf
@@ -4534,6 +4560,8 @@
sha256: 3c6a8936c77312f07a9ecb7b4bbbcb1f93ad137920ca6656bae9306571fb0c03 sha256: 3c6a8936c77312f07a9ecb7b4bbbcb1f93ad137920ca6656bae9306571fb0c03
uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-mini-f16.gguf uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-mini-f16.gguf
- name: ced-mini-q8 - name: ced-mini-q8
variants:
- model: ced-mini-f16
url: github:mudler/LocalAI/gallery/ced.yaml@master url: github:mudler/LocalAI/gallery/ced.yaml@master
urls: urls:
- https://huggingface.co/mudler/ced-gguf - https://huggingface.co/mudler/ced-gguf
@@ -4580,6 +4608,8 @@
sha256: c391ed8697a1b08d7c1a463e4940a5c3a2f670e0544ab0d8ee23b544583602a8 sha256: c391ed8697a1b08d7c1a463e4940a5c3a2f670e0544ab0d8ee23b544583602a8
uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-small-f16.gguf uri: https://huggingface.co/mudler/ced-gguf/resolve/main/ced-small-f16.gguf
- name: ced-small-q8 - name: ced-small-q8
variants:
- model: ced-small-f16
url: github:mudler/LocalAI/gallery/ced.yaml@master url: github:mudler/LocalAI/gallery/ced.yaml@master
urls: urls:
- https://huggingface.co/mudler/ced-gguf - https://huggingface.co/mudler/ced-gguf
@@ -6056,6 +6086,8 @@
uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
- !!merge <<: *qwenttscpp_gallery - !!merge <<: *qwenttscpp_gallery
name: qwen3-tts-cpp-1.7b-base name: qwen3-tts-cpp-1.7b-base
variants:
- model: qwen3-tts-cpp-1.7b-base-q4
description: | description: |
Qwen3-TTS 1.7B Base (C++ / GGML, qwentts.cpp), Q8_0 (~2.0 GB talker). Qwen3-TTS 1.7B Base (C++ / GGML, qwentts.cpp), Q8_0 (~2.0 GB talker).
Higher-quality streaming + voice cloning, 24kHz mono, 11 languages. 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 uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
- !!merge <<: *qwenttscpp_gallery - !!merge <<: *qwenttscpp_gallery
name: qwen3-tts-cpp-customvoice name: qwen3-tts-cpp-customvoice
variants:
- model: qwen3-tts-cpp-customvoice-q4
description: | description: |
Qwen3-TTS 0.6B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers Qwen3-TTS 0.6B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers
selected via the `voice` field: serena, vivian, uncle_fu, ryan, aiden, 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 uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
- !!merge <<: *qwenttscpp_gallery - !!merge <<: *qwenttscpp_gallery
name: qwen3-tts-cpp-1.7b-customvoice name: qwen3-tts-cpp-1.7b-customvoice
variants:
- model: qwen3-tts-cpp-1.7b-customvoice-q4
description: | description: |
Qwen3-TTS 1.7B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers via Qwen3-TTS 1.7B CustomVoice (C++ / GGML, qwentts.cpp), Q8_0. Named speakers via
the `voice` field (serena, vivian, ryan, aiden, eric, dylan, ...). Streaming, 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 uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
- !!merge <<: *qwenttscpp_gallery - !!merge <<: *qwenttscpp_gallery
name: qwen3-tts-cpp-1.7b-voicedesign name: qwen3-tts-cpp-1.7b-voicedesign
variants:
- model: qwen3-tts-cpp-1.7b-voicedesign-q4
description: | description: |
Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q8_0. Synthesises a Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q8_0. Synthesises a
speaker from a free-text attribute instruction - REQUIRES the OpenAI 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 uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q4_K_M.gguf
- &mossttscpp_gallery - &mossttscpp_gallery
name: moss-tts-cpp-v1_5-q8_0 name: moss-tts-cpp-v1_5-q8_0
variants:
- model: moss-tts-cpp-v1_5-f16
url: github:mudler/LocalAI/gallery/virtual.yaml@master url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: urls:
- https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF - 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 uri: huggingface://mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF/moss-tokenizer-v1_5.gguf
- !!merge <<: *mossttscpp_gallery - !!merge <<: *mossttscpp_gallery
name: moss-tts-cpp-v1_5-f16 name: moss-tts-cpp-v1_5-f16
variants: []
description: | description: |
MOSS-TTS-Local v1.5 (C++/ggml, moss-tts.cpp), F16 (~9.4 GB), code-exact versus the 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. reference. 48kHz stereo text-to-speech with reference-audio voice cloning.
@@ -8019,6 +8060,8 @@
sha256: cd5a851d3928697fa1bd76d459d2cc409b6cf40c9d9682b2f5c8e7c6a9f9630f sha256: cd5a851d3928697fa1bd76d459d2cc409b6cf40c9d9682b2f5c8e7c6a9f9630f
uri: huggingface://unsloth/Qwen3-VL-2B-Instruct-GGUF/mmproj-F16.gguf uri: huggingface://unsloth/Qwen3-VL-2B-Instruct-GGUF/mmproj-F16.gguf
- name: huihui-qwen3-vl-30b-a3b-instruct-abliterated - 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 url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/noctrex/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF - https://huggingface.co/noctrex/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF
@@ -8538,6 +8581,8 @@
sha256: c5c38bfa5d8d5100e91a2e0050a0b2f3e082cd4bfd423cb527abc3b6f1ae180c sha256: c5c38bfa5d8d5100e91a2e0050a0b2f3e082cd4bfd423cb527abc3b6f1ae180c
uri: huggingface://bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf 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 - name: opengvlab_internvl3_5-30b-a3b
variants:
- model: opengvlab_internvl3_5-30b-a3b-q8_0
url: github:mudler/LocalAI/gallery/qwen3.yaml@master url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B - https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B
@@ -8635,6 +8680,8 @@
sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d
uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf
- name: opengvlab_internvl3_5-14b - name: opengvlab_internvl3_5-14b
variants:
- model: opengvlab_internvl3_5-14b-q8_0
url: github:mudler/LocalAI/gallery/qwen3.yaml@master url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/OpenGVLab/InternVL3_5-14B - https://huggingface.co/OpenGVLab/InternVL3_5-14B
@@ -8667,6 +8714,8 @@
sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d sha256: c9625c981969d267052464e2d345f8ff5bc7e841871f5284a2bd972461c7356d
uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf uri: huggingface://bartowski/OpenGVLab_InternVL3_5-14B-GGUF/mmproj-OpenGVLab_InternVL3_5-14B-f16.gguf
- name: opengvlab_internvl3_5-8b - name: opengvlab_internvl3_5-8b
variants:
- model: opengvlab_internvl3_5-8b-q8_0
url: github:mudler/LocalAI/gallery/qwen3.yaml@master url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/OpenGVLab/InternVL3_5-8B - https://huggingface.co/OpenGVLab/InternVL3_5-8B
@@ -8729,6 +8778,8 @@
sha256: 212cc090f81ea2981b870186d4b424fae69489a5313a14e52ffdb2e877852389 sha256: 212cc090f81ea2981b870186d4b424fae69489a5313a14e52ffdb2e877852389
uri: huggingface://bartowski/OpenGVLab_InternVL3_5-8B-GGUF/mmproj-OpenGVLab_InternVL3_5-8B-f16.gguf uri: huggingface://bartowski/OpenGVLab_InternVL3_5-8B-GGUF/mmproj-OpenGVLab_InternVL3_5-8B-f16.gguf
- name: opengvlab_internvl3_5-4b - name: opengvlab_internvl3_5-4b
variants:
- model: opengvlab_internvl3_5-4b-q8_0
url: github:mudler/LocalAI/gallery/qwen3.yaml@master url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/OpenGVLab/InternVL3_5-4B - https://huggingface.co/OpenGVLab/InternVL3_5-4B
@@ -9956,6 +10007,8 @@
sha256: ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676 sha256: ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676
uri: https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx uri: https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx
- name: insightface-opencv - name: insightface-opencv
variants:
- model: insightface-opencv-int8
url: github:mudler/LocalAI/gallery/virtual.yaml@master url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: urls:
- https://github.com/opencv/opencv_zoo - https://github.com/opencv/opencv_zoo
@@ -10649,6 +10702,10 @@
sha256: 0909d8a1aba584b482d501baae032611d1559878be1b7f6606ba516687c5380d sha256: 0909d8a1aba584b482d501baae032611d1559878be1b7f6606ba516687c5380d
- &depth-anything-3-base - &depth-anything-3-base
name: 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 url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: urls:
- https://github.com/mudler/depth-anything.cpp - https://github.com/mudler/depth-anything.cpp
@@ -10680,6 +10737,7 @@
sha256: "43cd45d00f9024f4319f4beabd73155db5132e4b575bc52eff4131262c9d78f1" sha256: "43cd45d00f9024f4319f4beabd73155db5132e4b575bc52eff4131262c9d78f1"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-base-q8_0 name: depth-anything-3-base-q8_0
variants: []
description: | description: |
Depth Anything 3 (base), q8_0 — near-lossless 8-bit quant (~149 MB). Same 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. depth + camera pose output as the q4_k default at higher fidelity.
@@ -10693,6 +10751,7 @@
sha256: "71b1c953113657f9a4fbef43ab6a16fe7a6f87b36da113a184f13c4a564968a0" sha256: "71b1c953113657f9a4fbef43ab6a16fe7a6f87b36da113a184f13c4a564968a0"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-base-f16 name: depth-anything-3-base-f16
variants: []
description: | description: |
Depth Anything 3 (base), f16 — half precision (~233 MB), no measurable Depth Anything 3 (base), f16 — half precision (~233 MB), no measurable
accuracy loss vs f32. Depth + camera pose. accuracy loss vs f32. Depth + camera pose.
@@ -10706,6 +10765,7 @@
sha256: "2975419c99702ca646d5b7120c53e35c9fee158f0a803577241d16957f75624b" sha256: "2975419c99702ca646d5b7120c53e35c9fee158f0a803577241d16957f75624b"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-base-f32 name: depth-anything-3-base-f32
variants: []
description: | description: |
Depth Anything 3 (base), f32 — maximum fidelity (~412 MB). Reference-parity Depth Anything 3 (base), f32 — maximum fidelity (~412 MB). Reference-parity
depth + camera pose. depth + camera pose.
@@ -10719,6 +10779,7 @@
sha256: "1b13b166e8a8b4f2c862f42d36edb2f9aab995a18cc527a52b9f160b99c6b8da" sha256: "1b13b166e8a8b4f2c862f42d36edb2f9aab995a18cc527a52b9f160b99c6b8da"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-giant name: depth-anything-3-giant
variants: []
description: | description: |
Depth Anything 3 (giant / vitg), f32 — the large backbone (~4.9 GB) for Depth Anything 3 (giant / vitg), f32 — the large backbone (~4.9 GB) for
maximum quality depth + camera pose. GPU recommended. maximum quality depth + camera pose. GPU recommended.
@@ -10739,6 +10800,7 @@
sha256: "392edf64626be6a985487beb39c8d54cdc14f7feb2b53323742c96b71e7e7181" sha256: "392edf64626be6a985487beb39c8d54cdc14f7feb2b53323742c96b71e7e7181"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-small name: depth-anything-3-small
variants: []
description: | description: |
Depth Anything 3 (small / vits), f32 — the smallest backbone (~131 MB) for Depth Anything 3 (small / vits), f32 — the smallest backbone (~131 MB) for
fast CPU depth + camera pose. Same output as base at lower latency. fast CPU depth + camera pose. Same output as base at lower latency.
@@ -10752,6 +10814,7 @@
sha256: "eab5597e01dedde1a20c038590ae8c887b85ec35b882581138c08308e92c41e5" sha256: "eab5597e01dedde1a20c038590ae8c887b85ec35b882581138c08308e92c41e5"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-large name: depth-anything-3-large
variants: []
description: | description: |
Depth Anything 3 (large / vitl), f32 (~1.6 GB) — higher quality depth + Depth Anything 3 (large / vitl), f32 (~1.6 GB) — higher quality depth +
camera pose than base. GPU recommended for interactive use. camera pose than base. GPU recommended for interactive use.
@@ -10772,6 +10835,7 @@
sha256: "a79eb3e19e8ec49f4daac484fb5fb67e15baac61518d229cf819e40c87080906" sha256: "a79eb3e19e8ec49f4daac484fb5fb67e15baac61518d229cf819e40c87080906"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-mono-large name: depth-anything-3-mono-large
variants: []
description: | description: |
Depth Anything 3 (monocular large / vitl), f32 (~1.3 GB) — single-image 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 monocular depth + a sky mask (no camera pose). DPT single-head variant; use
@@ -10786,6 +10850,7 @@
sha256: "291b1a554af907c3f79986ee225da8933be5f7a31d73c81d06784cda284535de" sha256: "291b1a554af907c3f79986ee225da8933be5f7a31d73c81d06784cda284535de"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-metric-large name: depth-anything-3-metric-large
variants: []
description: | description: |
Depth Anything 3 (metric large / vitl), f32 (~1.3 GB) — single-image 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 metric-scale depth (meters) + a sky mask. DPT single-head metric variant; use
@@ -10801,6 +10866,7 @@
sha256: "d10b7450c2238244b2d72e2749537a1876255180149cd630a18bc1619c9286be" sha256: "d10b7450c2238244b2d72e2749537a1876255180149cd630a18bc1619c9286be"
- !!merge <<: *depth-anything-3-base - !!merge <<: *depth-anything-3-base
name: depth-anything-3-nested name: depth-anything-3-nested
variants: []
description: | description: |
Depth Anything 3 (nested giant+large), f32 — the recommended metric model. A 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 two-branch pipeline: the anyview GIANT (vitg) branch and a metric ViT-L branch
@@ -10832,6 +10898,10 @@
sha256: "b54ed50cbc0b0c14fae1f8edd0fea8bd1cac0850485fd6e7eb2422c7a19e570e" sha256: "b54ed50cbc0b0c14fae1f8edd0fea8bd1cac0850485fd6e7eb2422c7a19e570e"
- &depth-anything-2-base - &depth-anything-2-base
name: 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 url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: urls:
- https://github.com/mudler/depth-anything.cpp - https://github.com/mudler/depth-anything.cpp
@@ -10862,6 +10932,7 @@
sha256: "49e77ec7e593080111242fa76017cae3e26498d550841cf8a70dfcd36bb175f2" sha256: "49e77ec7e593080111242fa76017cae3e26498d550841cf8a70dfcd36bb175f2"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-base-q8_0 name: depth-anything-2-base-q8_0
variants: []
description: | description: |
Depth Anything V2 (base / ViT-B), q8_0 — near-lossless 8-bit quant. Same 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 relative monocular depth output as the q4_k default at higher fidelity. Use
@@ -10876,6 +10947,7 @@
sha256: "11920ec7a8dfc2fa7fe8ed44811a46fafe415c641d13144bb733d1437832291b" sha256: "11920ec7a8dfc2fa7fe8ed44811a46fafe415c641d13144bb733d1437832291b"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-base-f16 name: depth-anything-2-base-f16
variants: []
description: | description: |
Depth Anything V2 (base / ViT-B), f16 — half precision, no measurable Depth Anything V2 (base / ViT-B), f16 — half precision, no measurable
accuracy loss vs f32. Relative monocular depth only (no pose). Use accuracy loss vs f32. Relative monocular depth only (no pose). Use
@@ -10890,6 +10962,7 @@
sha256: "e91c011fbbf90a44639fea55b8d61ca9e80dfb5541220946c8b6e6261fe67ab1" sha256: "e91c011fbbf90a44639fea55b8d61ca9e80dfb5541220946c8b6e6261fe67ab1"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-base-f32 name: depth-anything-2-base-f32
variants: []
description: | description: |
Depth Anything V2 (base / ViT-B), f32 — maximum reference fidelity. Relative Depth Anything V2 (base / ViT-B), f32 — maximum reference fidelity. Relative
monocular depth only (no pose). Use GenerateImage (src -> depth PNG) or the monocular depth only (no pose). Use GenerateImage (src -> depth PNG) or the
@@ -10904,6 +10977,7 @@
sha256: "2d3d2e4d8fae9646c17577b84c870c7d77a34ded8cf8d5da0a60b2bee1530ccc" sha256: "2d3d2e4d8fae9646c17577b84c870c7d77a34ded8cf8d5da0a60b2bee1530ccc"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-small name: depth-anything-2-small
variants: []
description: | description: |
Depth Anything V2 (small / ViT-S), f32 — the smallest, fastest backbone for Depth Anything V2 (small / ViT-S), f32 — the smallest, fastest backbone for
relative monocular depth on CPU. Depth only (no pose). Use GenerateImage relative monocular depth on CPU. Depth only (no pose). Use GenerateImage
@@ -10918,6 +10992,7 @@
sha256: "1f6622aa70cbd0eba34d34e2f635a156ed8c3f8e158fb149eb355366e2deb899" sha256: "1f6622aa70cbd0eba34d34e2f635a156ed8c3f8e158fb149eb355366e2deb899"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-large name: depth-anything-2-large
variants: []
description: | description: |
Depth Anything V2 (large / ViT-L), f32 — higher-quality relative monocular Depth Anything V2 (large / ViT-L), f32 — higher-quality relative monocular
depth than base. Depth only (no pose). Use GenerateImage (src -> depth PNG) depth than base. Depth only (no pose). Use GenerateImage (src -> depth PNG)
@@ -10932,6 +11007,7 @@
sha256: "e187658b01b6df62e1553b03df9973606a7287551d4771b09802fc10b26f19f3" sha256: "e187658b01b6df62e1553b03df9973606a7287551d4771b09802fc10b26f19f3"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-hypersim-small name: depth-anything-2-metric-hypersim-small
variants: []
description: | description: |
Depth Anything V2 Metric (Hypersim, indoor / ViT-S), q4_k — metric monocular Depth Anything V2 Metric (Hypersim, indoor / ViT-S), q4_k — metric monocular
depth in METRES (indoor, max_depth 20). Depth only (no pose). Use depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
@@ -10953,6 +11029,7 @@
sha256: "decd99f5c756b564aae5ca1a1612f896e7f76889060e1d25ba610549bbc39b52" sha256: "decd99f5c756b564aae5ca1a1612f896e7f76889060e1d25ba610549bbc39b52"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-hypersim-base name: depth-anything-2-metric-hypersim-base
variants: []
description: | description: |
Depth Anything V2 Metric (Hypersim, indoor / ViT-B), q4_k — metric monocular Depth Anything V2 Metric (Hypersim, indoor / ViT-B), q4_k — metric monocular
depth in METRES (indoor, max_depth 20). Depth only (no pose). Use depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
@@ -10974,6 +11051,7 @@
sha256: "c7c6a8628ac154f2ad43db09b8146518e863375be2cb03b8b46caec49a4fcf3a" sha256: "c7c6a8628ac154f2ad43db09b8146518e863375be2cb03b8b46caec49a4fcf3a"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-hypersim-large name: depth-anything-2-metric-hypersim-large
variants: []
description: | description: |
Depth Anything V2 Metric (Hypersim, indoor / ViT-L), q4_k — highest-quality Depth Anything V2 Metric (Hypersim, indoor / ViT-L), q4_k — highest-quality
metric monocular depth in METRES (indoor, max_depth 20). Depth only (no metric monocular depth in METRES (indoor, max_depth 20). Depth only (no
@@ -10995,6 +11073,7 @@
sha256: "3664506bea55e64926fff2cb112ea5a9ad923d13647b9c69617184a89dd1e473" sha256: "3664506bea55e64926fff2cb112ea5a9ad923d13647b9c69617184a89dd1e473"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-vkitti-small name: depth-anything-2-metric-vkitti-small
variants: []
description: | description: |
Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-S), q4_k — metric 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 monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
@@ -11016,6 +11095,7 @@
sha256: "8dcaa5d0f8475c3dc5de59e28faacd6d46e5ef73c73ecc58e365d7751bc2279f" sha256: "8dcaa5d0f8475c3dc5de59e28faacd6d46e5ef73c73ecc58e365d7751bc2279f"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-vkitti-base name: depth-anything-2-metric-vkitti-base
variants: []
description: | description: |
Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-B), q4_k — metric 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 monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
@@ -11037,6 +11117,7 @@
sha256: "1de5a7aae674df6afb8fa5e06d67843dccfbab92cd64b7c816c1218229446d6d" sha256: "1de5a7aae674df6afb8fa5e06d67843dccfbab92cd64b7c816c1218229446d6d"
- !!merge <<: *depth-anything-2-base - !!merge <<: *depth-anything-2-base
name: depth-anything-2-metric-vkitti-large name: depth-anything-2-metric-vkitti-large
variants: []
description: | description: |
Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-L), q4_k — Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-L), q4_k —
highest-quality metric monocular depth in METRES (outdoor, max_depth 80). highest-quality metric monocular depth in METRES (outdoor, max_depth 80).
@@ -29035,6 +29116,8 @@
- &arch-router-1_5b - &arch-router-1_5b
url: github:mudler/LocalAI/gallery/chatml.yaml@master url: github:mudler/LocalAI/gallery/chatml.yaml@master
name: arch-router-1.5b-q4 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 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/66b681906c8d3b36786b764c/uyP7mxDVv0HbV9Hv_KfHk.jpeg
license: other license: other
urls: urls:
@@ -29080,6 +29163,7 @@
uri: huggingface://mradermacher/Arch-Router-1.5B-GGUF/Arch-Router-1.5B.Q4_K_M.gguf uri: huggingface://mradermacher/Arch-Router-1.5B-GGUF/Arch-Router-1.5B.Q4_K_M.gguf
- !!merge <<: *arch-router-1_5b - !!merge <<: *arch-router-1_5b
name: arch-router-1.5b-q8 name: arch-router-1.5b-q8
variants: []
overrides: overrides:
known_usecases: known_usecases:
- score - score
@@ -30660,6 +30744,9 @@
sha256: f4df16c641a05c4a6ca717068ba3ee312875000f6fac0efbd152915553b5fc3e sha256: f4df16c641a05c4a6ca717068ba3ee312875000f6fac0efbd152915553b5fc3e
uri: huggingface://second-state/stable-diffusion-3.5-large-GGUF/t5xxl-Q5_0.gguf uri: huggingface://second-state/stable-diffusion-3.5-large-GGUF/t5xxl-Q5_0.gguf
- name: flux.1-dev - 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 url: github:mudler/LocalAI/gallery/flux.yaml@master
urls: urls:
- https://huggingface.co/black-forest-labs/FLUX.1-dev - https://huggingface.co/black-forest-labs/FLUX.1-dev
@@ -30909,6 +30996,8 @@
sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635 sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
- name: flux.1-krea-dev-ggml - name: flux.1-krea-dev-ggml
variants:
- model: flux.1-krea-dev-ggml-q8_0
url: github:mudler/LocalAI/gallery/flux-ggml.yaml@master url: github:mudler/LocalAI/gallery/flux-ggml.yaml@master
urls: urls:
- https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev - https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev
@@ -31302,6 +31391,8 @@
sha256: 422f1ae452ade6f30a004d7e5c6a43195e4433bc370bf23fac9cc591f01a8898 sha256: 422f1ae452ade6f30a004d7e5c6a43195e4433bc370bf23fac9cc591f01a8898
uri: huggingface://ggerganov/whisper.cpp/ggml-base-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-base-q5_1.bin
- name: whisper-base - name: whisper-base
variants:
- model: whisper-base-q5_1
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31356,6 +31447,8 @@
sha256: 4baf70dd0d7c4247ba2b81fafd9c01005ac77c2f9ef064e00dcf195d0e2fdd2f sha256: 4baf70dd0d7c4247ba2b81fafd9c01005ac77c2f9ef064e00dcf195d0e2fdd2f
uri: huggingface://ggerganov/whisper.cpp/ggml-base.en-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-base.en-q5_1.bin
- name: whisper-base-en - name: whisper-base-en
variants:
- model: whisper-base-en-q5_1
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31410,6 +31503,8 @@
sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1 sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1
uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin
- name: whisper-medium - name: whisper-medium
variants:
- model: whisper-medium-q5_0
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31490,6 +31585,8 @@
sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb
uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin
- name: whisper-small - name: whisper-small
variants:
- model: whisper-small-q5_1
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31544,6 +31641,8 @@
sha256: bfdff4894dcb76bbf647d56263ea2a96645423f1669176f4844a1bf8e478ad30 sha256: bfdff4894dcb76bbf647d56263ea2a96645423f1669176f4844a1bf8e478ad30
uri: huggingface://ggerganov/whisper.cpp/ggml-small.en-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-small.en-q5_1.bin
- name: whisper-small-en - name: whisper-small-en
variants:
- model: whisper-small-en-q5_1
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31598,6 +31697,8 @@
sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb
uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-small-q5_1.bin
- name: whisper-tiny - name: whisper-tiny
variants:
- model: whisper-tiny-q5_1
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31677,6 +31778,9 @@
sha256: c77c5766f1cef09b6b7d47f21b546cbddd4157886b3b5d6d4f709e91e66c7c2b sha256: c77c5766f1cef09b6b7d47f21b546cbddd4157886b3b5d6d4f709e91e66c7c2b
uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q5_1.bin uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q5_1.bin
- name: whisper-tiny-en - 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 url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31728,6 +31832,8 @@
sha256: 5bc2b3860aa151a4c6e7bb095e1fcce7cf12c7b020ca08dcec0c6d018bb7dd94 sha256: 5bc2b3860aa151a4c6e7bb095e1fcce7cf12c7b020ca08dcec0c6d018bb7dd94
uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q8_0.bin uri: huggingface://ggerganov/whisper.cpp/ggml-tiny.en-q8_0.bin
- name: whisper-large - name: whisper-large
variants:
- model: whisper-large-q5_0
url: github:mudler/LocalAI/gallery/whisper-base.yaml@master url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -31781,6 +31887,9 @@
sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1 sha256: d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1
uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin uri: huggingface://ggerganov/whisper.cpp/ggml-large-v3-q5_0.bin
- name: whisper-large-turbo - 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 url: github:mudler/LocalAI/gallery/whisper-base.yaml@master
urls: urls:
- https://github.com/ggerganov/whisper.cpp - https://github.com/ggerganov/whisper.cpp
@@ -35020,6 +35129,8 @@
sha256: af8cb9e4ca0bf19eb54d08c612fdf325059264abbbd2c619527e5d2dda8de655 sha256: af8cb9e4ca0bf19eb54d08c612fdf325059264abbbd2c619527e5d2dda8de655
uri: https://huggingface.co/mradermacher/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.f16.gguf uri: https://huggingface.co/mradermacher/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.f16.gguf
- name: silero-vad - name: silero-vad
variants:
- model: silero-vad-ggml
url: github:mudler/LocalAI/gallery/virtual.yaml@master url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: urls:
- https://github.com/snakers4/silero-vad - https://github.com/snakers4/silero-vad
@@ -36314,6 +36425,8 @@
sha256: 0a599099e93ad521045e17d82365a73c1738fff0603d6cb2c9557e96fbc907cb sha256: 0a599099e93ad521045e17d82365a73c1738fff0603d6cb2c9557e96fbc907cb
uri: huggingface://mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF/YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf uri: huggingface://mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF/YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
- name: orca-agent-v0.1 - name: orca-agent-v0.1
variants:
- model: orca-agent-v0.1-i1
url: github:mudler/LocalAI/gallery/qwen3.yaml@master url: github:mudler/LocalAI/gallery/qwen3.yaml@master
urls: urls:
- https://huggingface.co/mradermacher/Orca-Agent-v0.1-GGUF - 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 uri: huggingface://unsloth/LTX-2.3-GGUF/text_encoders/ltx-2.3-22b-dev_embeddings_connectors.safetensors
- !!merge <<: *ltx-2-3-dev-ggml - !!merge <<: *ltx-2-3-dev-ggml
name: ltx-2.3-22b-dev-ggml-q4_k_m 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: | description: |
LTX-2.3 22B dev - non-dynamic Q4_K_M quantization (~14.3 GB). Same 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 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 uri: huggingface://unsloth/LTX-2.3-GGUF/text_encoders/ltx-2.3-22b-distilled_embeddings_connectors.safetensors
- !!merge <<: *ltx-2-3-distilled-ggml - !!merge <<: *ltx-2-3-distilled-ggml
name: ltx-2.3-22b-distilled-ggml-q4_k_m 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: | description: |
LTX-2.3 22B distilled - non-dynamic Q4_K_M quantization (~14.3 GB). 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 Same pipeline as ltx-2.3-22b-distilled-ggml but with the plain Q4_K_M