{"v":1,"id":"model:hf:abenzerps/Spark-X2.5-4B-GGUF","slug":"model-abenzerps-spark-x2-5-4b-gguf","kind":"model","category":"llm","title":"Spark-X2.5-4B-GGUF","summary":"Compatibility: These GGUF files require llama.cpp b10828 or later, which includes official support for the Spark-X2.5 (spark25) architecture. Applications with a bundled runtime must use an equivalen…","source":{"provider":"hf","ref":"abenzerps/Spark-X2.5-4B-GGUF","url":"https://huggingface.co/abenzerps/Spark-X2.5-4B-GGUF","rev":"f186f3d265c583a49d5e9d19bff23150b002202b","fetchedAt":"2026-10-09T19:01:15.510Z","etag":"W/\"2e11-cL0PW+MORqTVb+SIKhHcdO1KWLs\""},"author":{"name":"abenzerps","url":"https://huggingface.co/abenzerps"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":318878,"downloadsWeek":297971,"likes":24,"stars":130649,"openIssues":2491,"lastRelease":{"tag":"v0.6.0","at":"2026-10-05T16:56:22Z"},"pushedAt":"2026-10-09T18:49:42Z","takenAt":"2026-10-09T19:01:15.510Z"},"tags":["gguf","llama.cpp","spark-x2.5","long-context","1m-context","text-generation","conversational","endpoints_compatible"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-07T11:26:51.000Z","collectedAt":"2026-10-09T19:01:15.510Z","review":{"numbers":["318,878 downloads on Hugging Face","24 likes","license apache-2.0","2.4 GB for Spark-X2.5-4B-Q4_K_M.gguf","130,649 stars on ggml-org/llama.cpp","2,491 open issues and PRs","last release v0.6.0 on 2026-10-05","297,971 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-09T19:01:15.510Z","http":200},"description":"> [!IMPORTANT]\n> **Compatibility:** These GGUF files require `llama.cpp` **b10828** or later, which includes official support for the Spark-X2.5 (`spark2_5`) architecture. Applications with a bundled runtime must use an equivalent or newer build. [llama.cpp support](https://github.com/ggml-org/llama.cpp/pull/27868)\n\n# Spark-X2.5-4B GGUF\n\nGGUF quantizations of [XHToken/Spark-X2.5-4B](https://huggingface.co/XHToken/Spark-X2.5-4B), a 4B general-purpose language model for reasoning, coding, tool use, and agentic workflows. Native context: **1,048,576 tokens (1M)**.\n\n## Benchmarks\n\n*Benchmark results reported by XHToken for Spark-X2.5-4B in thinking mode.*\n\n## GGUF files\n\n| Quantization | File | Size |\n| --- | --- | ---: |\n| Q4_0 | [Spark-X2.5-4B-Q4_0.gguf](Spark-X2.5-4B-Q4_0.gguf) | 2.41 GB |\n| Q4_K_M | [Spark-X2.5-4B-Q4_K_M.gguf](Spark-X2.5-4B-Q4_K_M.gguf) | 2.60 GB |\n| Q5_K_M | [Spark-X2.5-4B-Q5_K_M.gguf](Spark-X2.5-4B-Q5_K_M.gguf) | 2.98 GB |\n| Q6_K | [Spark-X2.5-4B-Q6_K.gguf](Spark-X2.5-4B-Q6_K.gguf) | 3.38 GB |\n| Q8_0 | [Spark-X2.5-4B-Q8_0.gguf](Spark-X2.5-4B-Q8_0.gguf) | 4.38 GB |\n\nIncludes the upstream [chat_template.jinja](chat_template.jinja). Checksums: [SHA256SUMS.txt](SHA256SUMS.txt).\n\n## Usage\n\n```bash\nllama-cli -m Spark-X2.5-4B-Q4_K_M.gguf -c 131072 -cnv\n```\n\n## Source\n\n- Model: [XHToken/Spark-X2.5-4B](https://huggingface.co/XHToken/Spark-X2.5-4B)\n- Revision: `ea14618d20e76b5b093d3ee20a5b9d733bb12410`\n- License: [Apache-2.0](LICENSE)\n\nSource: https://huggingface.co/abenzerps/Spark-X2.5-4B-GGUF","install":{"kind":"model","hfId":"abenzerps/Spark-X2.5-4B-GGUF","gated":false,"format":"gguf","files":[{"name":"Spark-X2.5-4B-Q4_0.gguf","size":2405581632,"quant":"Q4_0","sha256":"33873ba76d69a72231ab0790d879cd252d53ee0fe648c3b44b04dec69fea25ec"},{"name":"Spark-X2.5-4B-Q4_K_M.gguf","size":2600223552,"quant":"Q4_K_M","sha256":"7934660bfc5b9bf04be0a0ac6179a1d16e1d4331b448857c86b8b2801b3ef72c"},{"name":"Spark-X2.5-4B-Q5_K_M.gguf","size":2977895232,"quant":"Q5_K_M","sha256":"d585f155289ed7b73f2f644e475445fcc40f1aa5131ca807eade1c726895535a"},{"name":"Spark-X2.5-4B-Q6_K.gguf","size":3379171392,"quant":"Q6_K","sha256":"7293e99081e032b30e481c159aa35b3f7d133a746c1096910024ea71fff82246"},{"name":"Spark-X2.5-4B-Q8_0.gguf","size":4375020352,"quant":"Q8_0","sha256":"58a4fc627cc2b2cbea02f81fb22960938e86bf3e62a2b3ae01c55a678481d46b"}],"totalBytes":15737892160,"suggestedFile":"Spark-X2.5-4B-Q4_K_M.gguf","requirements":{"ramGb":4,"diskBytes":2600223552,"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:abenzerps/Spark-X2.5-4B-GGUF"}}