feat(gallery): add Ornith 1.5 122B variants

Add pinned UD-Q4_K_XL and Q8_0 builds with the vision projector and installation documentation. Assisted-by: Codex:gpt-6 (cherry picked from commit 31978a28ef, mudler/LocalAI#12809) Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-10-28 09:08:54 -04:00 · 2026-10-25 09:55:39 +00:00
1 parent db9e20967c
commit e2925e20ef
@@ -3,6 +3,123 @@
 # written by scripts/models/cmd/modelcatalog and stays only so releases before
 # the cutover keep working. CI fails when it differs from the generated copy:
 #   go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: ornith-1.5-122b-ud-q4-k-xl
+  description: |
+    Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
+    coding, and tool use. This UD-Q4_K_XL GGUF build includes the F16 vision
+    projector for image input and uses an 8,192-token default context.
+  license: mit
+  urls:
+    - https://huggingface.co/ornith-ai/Ornith-1.5-122B
+    - https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - moe
+    - reasoning
+    - coding
+    - tools
+    - vision
+  files:
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+      sha256: 7159d31a6a6ce5528500b490880383844c3c9b21fcdaad94e66c9e65233ff359
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf
+      sha256: e66952128394bb4c75554c7e10a12a8b63dd1c7f049d876a02885a946e30c1c3
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00003-of-00003.gguf
+      sha256: 21325ec18a9e3210eeffada0fc327a25a79171918f1d04f8f0a06b61866ac9ba
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00003-of-00003.gguf
+    - filename: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+      sha256: 39db176176a904b101f5173a4f03e785990f9279f94ab373c4fd629ae7011817
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/mmproj-F16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 8192
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  variants:
+    - model: ornith-1.5-122b-q8
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: ornith-1.5-122b-q8
+  description: |
+    Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
+    coding, and tool use. This Q8_0 GGUF build includes the F16 vision
+    projector for image input and uses an 8,192-token default context.
+  license: mit
+  urls:
+    - https://huggingface.co/ornith-ai/Ornith-1.5-122B
+    - https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - moe
+    - reasoning
+    - coding
+    - tools
+    - vision
+  files:
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+      sha256: e9dbc5401757506c6bbb04dba3bf65decc6435aaf0733f1e95cc58a9332166fc
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00002-of-00004.gguf
+      sha256: c1ea340f63c932895417f7c2e7c4967b4b56f3e5a3f981242d0482c662aae2b8
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00002-of-00004.gguf
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00003-of-00004.gguf
+      sha256: 644c26a3d8cab405186ef545e4071b433a23c2a359e45434c822d9c48884eb4c
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00003-of-00004.gguf
+    - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00004-of-00004.gguf
+      sha256: 43bdc1b0cb764b5531d320816fb6004245256a414bfd55f1fdb69e3db42eaa57
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00004-of-00004.gguf
+    - filename: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+      sha256: 39db176176a904b101f5173a4f03e785990f9279f94ab373c4fd629ae7011817
+      uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/mmproj-F16.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 8192
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
 - url: github:mudler/LocalAI/gallery/virtual.yaml@master
  name: deepseek-v4.1-flash-1017
  description: "# DeepSeek-V4.1-Flash-1017\n\nTechnical Report \U0001F441️\n\n## Introduction\n\n**DeepSeek-V4.1-Flash-1017** is a minor update to **DeepSeek-V4.1-Flash**, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.\n\n*† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.*\n\n## Prompt Encoding\n\nThis release does not include a Jinja-format chat template. The `encoding` folder contains a self-contained Python reference implementation (`encoding.py`) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.\n\n...\n"
@@ -4,6 +4,139 @@
 # changes and never edit it by hand. CI fails when it is stale. A build from
 # master reads it as the default model source; a tagged build reads the gallery
 # until the release cutover.
+- kind: model
+  id: ornith-1.5-122b-ud-q4-k-xl
+  name: ornith-1.5-122b-ud-q4-k-xl
+  version: 0.0.0-gallery.a2e3fad41cfd
+  description: |
+    Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
+    coding, and tool use. This UD-Q4_K_XL GGUF build includes the F16 vision
+    projector for image input and uses an 8,192-token default context.
+  license: mit
+  urls:
+    - https://huggingface.co/ornith-ai/Ornith-1.5-122B
+    - https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - moe
+    - reasoning
+    - coding
+    - tools
+    - vision
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+        sha256: 7159d31a6a6ce5528500b490880383844c3c9b21fcdaad94e66c9e65233ff359
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf
+        sha256: e66952128394bb4c75554c7e10a12a8b63dd1c7f049d876a02885a946e30c1c3
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00003-of-00003.gguf
+        sha256: 21325ec18a9e3210eeffada0fc327a25a79171918f1d04f8f0a06b61866ac9ba
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/UD-Q4_K_XL/Ornith-1.5-122B-UD-Q4_K_XL-00003-of-00003.gguf
+      - filename: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+        sha256: 39db176176a904b101f5173a4f03e785990f9279f94ab373c4fd629ae7011817
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/mmproj-F16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 8192
+      function:
+        automatic_tool_parsing_fallback: true
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+        - vision
+      mmproj: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+      options:
+        - use_jinja:true
+      parameters:
+        min_p: 0
+        model: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-UD-Q4_K_XL-00001-of-00003.gguf
+        repeat_penalty: 1
+        temperature: 0.6
+        top_k: 20
+        top_p: 0.95
+      template:
+        use_tokenizer_template: true
+    variants:
+      - model: ornith-1.5-122b-q8
+- kind: model
+  id: ornith-1.5-122b-q8
+  name: ornith-1.5-122b-q8
+  version: 0.0.0-gallery.c413535d0838
+  description: |
+    Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
+    coding, and tool use. This Q8_0 GGUF build includes the F16 vision
+    projector for image input and uses an 8,192-token default context.
+  license: mit
+  urls:
+    - https://huggingface.co/ornith-ai/Ornith-1.5-122B
+    - https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - moe
+    - reasoning
+    - coding
+    - tools
+    - vision
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+        sha256: e9dbc5401757506c6bbb04dba3bf65decc6435aaf0733f1e95cc58a9332166fc
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00002-of-00004.gguf
+        sha256: c1ea340f63c932895417f7c2e7c4967b4b56f3e5a3f981242d0482c662aae2b8
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00002-of-00004.gguf
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00003-of-00004.gguf
+        sha256: 644c26a3d8cab405186ef545e4071b433a23c2a359e45434c822d9c48884eb4c
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00003-of-00004.gguf
+      - filename: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00004-of-00004.gguf
+        sha256: 43bdc1b0cb764b5531d320816fb6004245256a414bfd55f1fdb69e3db42eaa57
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/Q8_0/Ornith-1.5-122B-Q8_0-00004-of-00004.gguf
+      - filename: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+        sha256: 39db176176a904b101f5173a4f03e785990f9279f94ab373c4fd629ae7011817
+        uri: https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF/resolve/3842d003341507c216295c6f28dfcd30349925c6/mmproj-F16.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 8192
+      function:
+        automatic_tool_parsing_fallback: true
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+        - vision
+      mmproj: llama-cpp/mmproj/ornith-1.5-122b/mmproj-F16.gguf
+      options:
+        - use_jinja:true
+      parameters:
+        min_p: 0
+        model: llama-cpp/models/ornith-1.5-122b/Ornith-1.5-122B-Q8_0-00001-of-00004.gguf
+        repeat_penalty: 1
+        temperature: 0.6
+        top_k: 20
+        top_p: 0.95
+      template:
+        use_tokenizer_template: true
 - kind: model
  id: deepseek-v4.1-flash-1017
  name: deepseek-v4.1-flash-1017