{"v":1,"id":"model:hf:XHToken/Spark-X2.5-4B-GGUF","slug":"model-xhtoken-spark-x2-5-4b-gguf","kind":"model","category":"llm","title":"Spark-X2.5-4B-GGUF","summary":"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…","source":{"provider":"hf","ref":"XHToken/Spark-X2.5-4B-GGUF","url":"https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF","rev":"9826e0be84e6e6e8b9668abc91421109a1df1e2d","fetchedAt":"2026-10-02T20:53:26.193Z","etag":"W/\"1d1d-CI9bOfqEGChp3aWTtX7TYsR+R+s\""},"author":{"name":"XHToken","url":"https://huggingface.co/XHToken"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":466393,"downloadsWeek":327838,"likes":256,"stars":130156,"openIssues":2528,"lastRelease":{"tag":"v0.5.0","at":"2026-09-23T20:50:06Z"},"pushedAt":"2026-10-02T20:17:08Z","takenAt":"2026-10-02T20:53:26.193Z"},"tags":["gguf","llama.cpp","ollama","lm-studio","sparkx2_5","unsloth","pocketpal-ai","text-generation","en","zh","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-20T08:08:37.000Z","collectedAt":"2026-10-02T20:53:26.193Z","review":{"numbers":["466,393 downloads on Hugging Face","256 likes","license apache-2.0","2.4 GB for Spark-X2.5-4B-Q4_K_M.gguf","130,156 stars on ggml-org/llama.cpp","2,528 open issues and PRs","last release v0.5.0 on 2026-09-23","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:53:26.193Z","http":200},"description":"# Spark-X2.5-4B-GGUF\n\nSpark-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](https://huggingface.co/XHToken/Spark-X2.5-4B).\n\n## Local Deployment\n\n### llama.cpp\n\n> [!NOTE]\n> Native `spark2_5` support requires [llama.cpp](https://github.com/ggml-org/llama.cpp/) `b10828` or later.\n\nRun the model in the CLI:\n```bash\nllama cli -m /path/to/Spark-X2.5-4B-GGUF\n```\n\nLaunch the OpenAI-compatible API server:\n```bash\nllama serve -m /path/to/Spark-X2.5-4B-GGUF\n```\n\n### Ollama\n\n[Download Ollama](https://ollama.com/download)\n\n> [!NOTE]\n> Native `spark2_5` support requires Ollama [`v0.34.1`](https://github.com/ollama/ollama/releases) or later.\n\n```bash\nollama run SparkLLM/Spark-X2.5-4B\n```\n\n### LM Studio\n\n[Download LM Studio](https://lmstudio.ai/download)\n\n> [!NOTE]\n> Native `spark2_5` support requires runtime version `2.34.0` or later.\n\n### Unsloth\n\n[Download Unsloth Studio](https://unsloth.ai/)\n\n> [!NOTE]\n> The latest Unsloth Studio supports native Spark-X2.5 GGUF inference.\n\n## License\n\nReleased under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).\n\nSource: https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF","install":{"kind":"model","hfId":"XHToken/Spark-X2.5-4B-GGUF","gated":false,"format":"gguf","files":[{"name":"Spark-X2.5-4B-Q4_K_M.gguf","size":2600224352,"quant":"Q4_K_M","sha256":"adfcfa19a4ed6a5985da8bf565fe15f8e1a7e131d79bae2d19d48d1c40109428"},{"name":"Spark-X2.5-4B-Q8_0.gguf","size":4375021152,"quant":"Q8_0","sha256":"5c2c3c190e4337e1016b8593ca8e26e8b18c972200b107385d4ec61a25d9dea2"},{"name":"Spark-X2.5-4B.gguf","size":8229920352,"sha256":"8cecf405a41a4a10f833530910c2e13fde9fb39c325c8afc3c5d10e4181e1a14"}],"totalBytes":15205165856,"suggestedFile":"Spark-X2.5-4B-Q4_K_M.gguf","requirements":{"ramGb":4,"diskBytes":2600224352,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:XHToken/Spark-X2.5-4B-GGUF"}}