XHToken/Spark-X2.5-4B-GGUF
text-generationggufVerified checksumsggufllama.cppollamalm-studiosparkx2_5text-generation
- License
- apache-2.0
- Size
- 14 GB
- Revision
- main
Mirrored from XHToken/Spark-X2.5-4B-GGUF
All models by XHToken →Mirrored from XHToken/Spark-X2.5-4B-GGUF
All models by XHToken →[!NOTE] This repository provides a BF16 GGUF conversion of Spark-X2.5-4B.
Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. It uses a hybrid attention architecture, supports a native context length of up to 1M tokens, and covers more than 200 languages. For its architecture, training methods, benchmark results, fine-tuning, and citation, see the Spark-X2.5-4B.
The GGUF file can be used for local inference with Ollama and LM Studio. Spark-X2.5 support is provided by XHToken/llama.cpp, so the Quick Starts below use this compatible implementation.
Replace the model path below with the absolute path to the downloaded GGUF file:
Start the Ollama server in the first terminal:
Open a second terminal in the same ollama-spark directory:
--think=false disables thinking mode for faster, direct responses.
Close LM Studio.
Back up the selected LM Studio runtime directory:
Copy the llama.cpp-spark build output into the selected runtime directory, replacing the existing runtime files.
Place Spark-X2.5-4B.gguf in:
Example runtime directory on Apple Silicon:
Open LM Studio, select the model under My Models, click Load, and start a new chat.
You can also use the lms CLI:
Released under the Apache License 2.0.
git clone https://github.com/XHToken/llama.cpp.git llama.cpp-sparkgit clone https://github.com/ollama/ollama.git ollama-sparkcd ollama-sparkexport OLLAMA_LLAMA_CPP_SOURCE="$(cd ../llama.cpp-spark && pwd)"cmake -S . -B buildcmake --build build --parallel 8printf 'FROM /absolute/path/to/Spark-X2.5-4B.gguf\n' > ./Modelfile.spark./ollama serve./ollama create Spark-X2.5-4B -f ./Modelfile.spark./ollama run Spark-X2.5-4B --think=falsegit clone https://github.com/XHToken/llama.cpp.git llama.cpp-sparkcd llama.cpp-sparkcmake -S . -B buildcmake --build build --parallel 8<LM_STUDIO_HOME>/extensions/backends/<selected-runtime>/<LM_STUDIO_HOME>/models/<org>/<name>/./build/bin/* -> ~/.lmstudio/extensions/backends/llama.cpp-mac-arm64-apple-metal-advsimd-<version>/lms lslms load <model>lms chat <model>