From 4207c9600a57edff7f0dd560755a2762b175c13d Mon Sep 17 00:00:00 2001 From: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> Date: Mon, 21 Sep 2026 00:07:55 +0000 Subject: [PATCH] feat(gallery): add Maple-Preview GGUF variants Offer four ternary builds through the existing llama.cpp backend. Use the publisher's CPU settings and embedded chat template. Pin downloads and verify SHA256 values against two HF metadata sources. Document installation and explicit variant selection. Assisted-by: Codex:gpt-6 --- docs/content/features/model-gallery.md | 21 ++++ gallery/index.yaml | 144 +++++++++++++++++++++++++ 2 files changed, 165 insertions(+) diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index bc8e524c6..9cd60541b 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -54,6 +54,27 @@ Both views use the same model selection and store the view, search, filter, and selection in the URL. Installing from Explore does not move you away from the catalog; the entry updates in place when the operation finishes. +## Maple-Preview + +[Maple-Preview](https://huggingface.co/deepgrove/maple-preview-GGUF) is a 20B reasoning model with about 1B active parameters. +Install it with automatic selection among four ternary GGUF builds: + +```bash +local-ai models install maple-preview-tq1-0-head-q4-k +``` + +The variants combine TQ1_0 or TQ2_0 weights with a Q4_K or F16 output head. +To select a build explicitly: + +```bash +local-ai models install maple-preview-tq1-0-head-q4-k --variant maple-preview-tq2-0-head-q4-k +``` + +These entries use llama.cpp with the publisher's CPU configuration, sampling settings, and embedded Jinja chat template. +The default context is 8,192 tokens; the model supports up to 131,072 tokens with sufficient memory. +Use a current llama.cpp backend that includes the Maple architecture. +Downloads use a pinned revision and SHA256 checksums. + ## NeoHorse-1-4B Install NeoHorse-1-4B with automatic selection between Q4_K_M, Q6_K, and Q8_0 GGUF builds: diff --git a/gallery/index.yaml b/gallery/index.yaml index 04fa669b6..db5a01988 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -15032,6 +15032,150 @@ - filename: llama-cpp/mmproj/mmproj-Qwen_Qwen3.5-2B-f16.gguf sha256: 044a0ea136cca70711ae16e23b24d754b44eab6f2462d187aee4d7c7a9503d36 uri: https://huggingface.co/bartowski/Qwen_Qwen3.5-2B-GGUF/resolve/main/mmproj-Qwen_Qwen3.5-2B-f16.gguf +- name: maple-preview-tq1-0-head-q4-k + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/deepgrove/maple-preview + - https://huggingface.co/deepgrove/maple-preview-GGUF + license: mit + description: | + Maple-Preview is DeepGrove's 20B mixture-of-experts reasoning model + with about 1B active parameters. This build uses TQ1_0 + ternary GGUF weights with a Q4_K output head. + It uses the publisher's CPU configuration and embedded Jinja chat + template with an 8K default context. The native context is 128K tokens. + tags: + - llm + - gguf + - cpu + - reasoning + variants: + - model: maple-preview-tq1-0-head-f16 + - model: maple-preview-tq2-0-head-q4-k + - model: maple-preview-tq2-0-head-f16 + overrides: + backend: llama-cpp + context_size: 8192 + gpu_layers: 0 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: maple-preview-TQ1_0-head-Q4_K.gguf + temperature: 1 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: maple-preview-TQ1_0-head-Q4_K.gguf + uri: https://huggingface.co/deepgrove/maple-preview-GGUF/resolve/f5466f918e0c50cdb9d4d47a6f35813509a42a30/maple-preview-TQ1_0-head-Q4_K.gguf + sha256: 54016e4d543bd688829e67103fc85b8396db94b7f8eb3f81fa95884e44393872 +- name: maple-preview-tq1-0-head-f16 + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/deepgrove/maple-preview + - https://huggingface.co/deepgrove/maple-preview-GGUF + license: mit + description: | + Maple-Preview is DeepGrove's 20B mixture-of-experts reasoning model + with about 1B active parameters. This build uses TQ1_0 + ternary GGUF weights with a F16 output head. + It uses the publisher's CPU configuration and embedded Jinja chat + template with an 8K default context. The native context is 128K tokens. + tags: + - llm + - gguf + - cpu + - reasoning + overrides: + backend: llama-cpp + context_size: 8192 + gpu_layers: 0 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: maple-preview-TQ1_0-head-F16.gguf + temperature: 1 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: maple-preview-TQ1_0-head-F16.gguf + uri: https://huggingface.co/deepgrove/maple-preview-GGUF/resolve/f5466f918e0c50cdb9d4d47a6f35813509a42a30/maple-preview-TQ1_0-head-F16.gguf + sha256: c20ecf619b2fd599d5dc6562cfc047b2b389e613d440a7771ccbf8eadac0d084 +- name: maple-preview-tq2-0-head-q4-k + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/deepgrove/maple-preview + - https://huggingface.co/deepgrove/maple-preview-GGUF + license: mit + description: | + Maple-Preview is DeepGrove's 20B mixture-of-experts reasoning model + with about 1B active parameters. This build uses TQ2_0 + ternary GGUF weights with a Q4_K output head. + It uses the publisher's CPU configuration and embedded Jinja chat + template with an 8K default context. The native context is 128K tokens. + tags: + - llm + - gguf + - cpu + - reasoning + overrides: + backend: llama-cpp + context_size: 8192 + gpu_layers: 0 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: maple-preview-TQ2_0-head-Q4_K.gguf + temperature: 1 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: maple-preview-TQ2_0-head-Q4_K.gguf + uri: https://huggingface.co/deepgrove/maple-preview-GGUF/resolve/f5466f918e0c50cdb9d4d47a6f35813509a42a30/maple-preview-TQ2_0-head-Q4_K.gguf + sha256: 221f792cc9760d27a34f449b4229e258fa968a63bd4213993e45d9c0bb477a9e +- name: maple-preview-tq2-0-head-f16 + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/deepgrove/maple-preview + - https://huggingface.co/deepgrove/maple-preview-GGUF + license: mit + description: | + Maple-Preview is DeepGrove's 20B mixture-of-experts reasoning model + with about 1B active parameters. This build uses TQ2_0 + ternary GGUF weights with a F16 output head. + It uses the publisher's CPU configuration and embedded Jinja chat + template with an 8K default context. The native context is 128K tokens. + tags: + - llm + - gguf + - cpu + - reasoning + overrides: + backend: llama-cpp + context_size: 8192 + gpu_layers: 0 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: maple-preview-TQ2_0-head-F16.gguf + temperature: 1 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: maple-preview-TQ2_0-head-F16.gguf + uri: https://huggingface.co/deepgrove/maple-preview-GGUF/resolve/f5466f918e0c50cdb9d4d47a6f35813509a42a30/maple-preview-TQ2_0-head-F16.gguf + sha256: 2fad7b4903781aca6b1171881f2d273989fe1735b6b3ea704bc486b472d98039 - &neohorse-1-4b name: neohorse-1-4b-q4 url: github:mudler/LocalAI/gallery/virtual.yaml@master