From ab191912e95b98b831ee720e322b75d84248216e Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 11 Sep 2026 22:37:11 +0000 Subject: [PATCH] gallery: apply PR #11926 Assisted-by: localai-org-maint-bot:glm5.2 [gh] --- docs/content/features/model-gallery.md | 16 +++--- gallery/index.yaml | 70 ++++++++------------------ 2 files changed, 29 insertions(+), 57 deletions(-) diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index 8e15df599..d2561dab0 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -43,26 +43,26 @@ 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. -## Spark-X2.5-4B +## Spark-X2.5-1.7B -Install Spark-X2.5-4B with automatic selection between its Q4_K_M, Q6_K, -and Q8_0 GGUF builds: +Install Spark-X2.5-1.7B with automatic selection between its Q4_K_M and Q8_0 +GGUF builds: ```bash -local-ai models install spark-x2.5-4b-q4 +local-ai models install spark-x2.5-1.7b-q4 ``` -To select a quantization explicitly: +To select the Q8_0 build explicitly: ```bash -local-ai models install spark-x2.5-4b-q4 --variant spark-x2.5-4b-q6 +local-ai models install spark-x2.5-1.7b-q4 --variant spark-x2.5-1.7b-q8 ``` These text-only builds use the llama.cpp backend and the embedded Jinja chat template. The gallery defaults to a 32,768-token context to limit memory use. -The [source model](https://huggingface.co/XHToken/Spark-X2.5-4B) supports up to +The [source model](https://huggingface.co/XHToken/Spark-X2.5-1.7B) supports up to 1,048,576 tokens; larger contexts require more memory. Use a current LocalAI -llama.cpp backend with Spark-X2.5 support (upstream b10828 or later). +llama.cpp backend with Spark-X2.5 support. ## VRAM and download size estimates diff --git a/gallery/index.yaml b/gallery/index.yaml index fcc170f2f..571587635 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3870,20 +3870,18 @@ - filename: llama-cpp/mmproj/qwen3.8-27b-gsq-rco/mmproj-Qwen3.8-27B-BF16.gguf uri: huggingface://ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/mmproj-Qwen3.8-27B-BF16.gguf sha256: 13cb7bebccbd04afc8f4090cb949ecf8937cdf7377c5799b1a0c594e7c0d3e16 -- &spark-x2-5-4b - name: "spark-x2.5-4b-q4" +- &spark-x2-5-1-7b + name: "spark-x2.5-1.7b-q4" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" variants: - - model: spark-x2.5-4b-q6 - - model: spark-x2.5-4b-q8 + - model: spark-x2.5-1.7b-q8 urls: - - https://huggingface.co/XHToken/Spark-X2.5-4B - - https://huggingface.co/abenzerps/Spark-X2.5-4B-GGUF + - https://huggingface.co/XHToken/Spark-X2.5-1.7B + - https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF description: | - Spark-X2.5-4B is XHToken's 4B text model for conversation, reasoning, - coding, and multilingual tasks. This entry uses Q4_K_M GGUF weights; - Q6_K and Q8_0 builds are available as variants. All builds use the - embedded Jinja chat template and a 32K-token default context. + Spark-X2.5-1.7B is XHToken's 1.7B text model for conversation, reasoning, + coding, and multilingual tasks. This build uses Q4_K_M GGUF weights, + the embedded Jinja chat template, and a 32K-token default context. license: "apache-2.0" tags: - llm @@ -3902,7 +3900,7 @@ options: - use_jinja:true parameters: - model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf + model: llama-cpp/models/spark-x2.5-1.7b/Spark-X2.5-1.7B-Q4_K_M.gguf temperature: 1 top_p: 0.95 top_k: -1 @@ -3911,16 +3909,17 @@ template: use_tokenizer_template: true files: - - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf - uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q4_K_M.gguf - sha256: 7934660bfc5b9bf04be0a0ac6179a1d16e1d4331b448857c86b8b2801b3ef72c + - filename: llama-cpp/models/spark-x2.5-1.7b/Spark-X2.5-1.7B-Q4_K_M.gguf + uri: huggingface://XHToken/Spark-X2.5-1.7B-GGUF/Spark-X2.5-1.7B-Q4_K_M.gguf + sha256: 902bde2522394954ac17821b3e5fd0df02defbc6944f122253f2580acf0503f4 -- !!merge <<: *spark-x2-5-4b - name: "spark-x2.5-4b-q6" +- !!merge <<: *spark-x2-5-1-7b + name: "spark-x2.5-1.7b-q8" variants: [] description: | - Spark-X2.5-4B in Q6_K GGUF format, with the embedded Jinja chat - template and a 32K-token default context. + Spark-X2.5-1.7B is XHToken's 1.7B text model for conversation, reasoning, + coding, and multilingual tasks. This build uses Q8_0 GGUF weights, + the embedded Jinja chat template, and a 32K-token default context. overrides: backend: llama-cpp context_size: 32768 @@ -3929,7 +3928,7 @@ options: - use_jinja:true parameters: - model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf + model: llama-cpp/models/spark-x2.5-1.7b/Spark-X2.5-1.7B-Q8_0.gguf temperature: 1 top_p: 0.95 top_k: -1 @@ -3938,36 +3937,9 @@ template: use_tokenizer_template: true files: - - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf - uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q6_K.gguf - sha256: 7293e99081e032b30e481c159aa35b3f7d133a746c1096910024ea71fff82246 - -- !!merge <<: *spark-x2-5-4b - name: "spark-x2.5-4b-q8" - variants: [] - description: | - Spark-X2.5-4B in Q8_0 GGUF format, with the embedded Jinja chat - template and a 32K-token default context. - overrides: - backend: llama-cpp - context_size: 32768 - known_usecases: - - chat - options: - - use_jinja:true - parameters: - model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf - temperature: 1 - top_p: 0.95 - top_k: -1 - min_p: 0 - repeat_penalty: 1 - template: - use_tokenizer_template: true - files: - - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf - uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q8_0.gguf - sha256: 58a4fc627cc2b2cbea02f81fb22960938e86bf3e62a2b3ae01c55a678481d46b + - filename: llama-cpp/models/spark-x2.5-1.7b/Spark-X2.5-1.7B-Q8_0.gguf + uri: huggingface://XHToken/Spark-X2.5-1.7B-GGUF/Spark-X2.5-1.7B-Q8_0.gguf + sha256: cd77c03185a834bb1162a4b7713520be5838058bfc54873645beff470bb24442 - &qwen3-8-9b name: "qwen3.8-9b-q4"