{"slug": "spark-x2-5", "title": "Spark-X2.5", "summary": "XHToken released the Spark-X2.5 open model series, including Spark-X2.5-4B and Spark-X2.5-1.7B, two compact general-purpose language models with native context windows of up to 1M tokens and support for more than 200 languages. The models use a hybrid attention architecture combining one full-attention layer with three sliding-window attention layers, were trained on Huawei Ascend clusters, and are compatible with vLLM, SGLang, llama.cpp, MLX, Ollama, LM Studio and LLaMA-Factory across NVIDIA, Huawei, Hygon and HOUMO.AI hardware. The global launch on Hugging Face, ModelScope, Ollama, Modelers and SCNet was followed by FP8 and INT8 quantized versions on 2026/09/04 and native llama.cpp support (Spark2_5ForCausalLM) on 2026/09/06.", "body_md": "Welcome to the GitHub repository of Spark-X2.5 open model series. You can find official information about Spark-X2.5, and post your questions [here(Issues)](https://github.com/XHToken/Spark-X2.5/issues).\n\nToday, we are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose language models designed to make capable AI more practical, efficient, and accessible. The models deliver strong performance across a broad range of everyday tasks—including conversation, writing, translation, reasoning, coding, tool use, and agentic workflows—achieving leading results among open-source models of comparable size. Spark-X2.5 combines an efficiency-oriented architecture with native context windows of up to 1M tokens, and support for more than 200 languages.\n\n**Technical Highlights**:\n\n- **Efficient Architecture and Native 1M-token Context** : The models use a hybrid attention architecture that combines one full-attention layer with three sliding-window attention layers. This design substantially reduces the computational overhead typically associated with long-context models while natively supporting a context window of up to 1M tokens.\n- **Strong Coding and Agent Capabilities** : The models are deeply integrated with popular agent harnesses, including Codex, Claude Code, OpenClaw, and Hermes. They deliver state-of-the-art performance among models of comparable size across everyday coding, agentic workflows, reasoning, and instruction-following tasks.\n- **Broad Hardware and Software Compatibility** : The models support a wide range of hardware platforms, including NVIDIA, Huawei, Hygon, HOUMO.AI, etc. It is compatible with leading inference frameworks such as vLLM, SGLang, llama.cpp, MLX, and can be deployed quickly through platforms including Ollama and LM Studio. The models can also be customized using popular fine-tuning frameworks such as LLaMA-Factory. Across multiple hardware platforms, they deliver superior TTFT, TOPT, and overall inference efficiency compared with similarly sized models.\n- **Advanced Training Algorithms** : The models were trained on Huawei Ascend clusters. Large-scale reinforcement learning and post-training techniques such as MOPD significantly enhance its reasoning, coding, agentic, and instruction-following capabilities.\n\n- [2026/09/15] 🤝 Added [ollama](https://github.com/ollama/ollama/releases/tag/v0.34.1) support for Spark-X2.5 model architecture.\n- [2026/09/11] 🚀 Added native support for Spark-X2.5 model in PocketPal AI app, now available on [App Store](https://apps.apple.com/us/app/pocketpal-ai/id6502579498) and[Google Play](https://play.google.com/store/apps/details?id=com.pocketpalai) .\n- [2026/09/08] 🤝 Added [LM Studio](https://lmstudio.ai/download) support for Spark-X2.5 model architecture.\n- [2026/09/06] 🤝 Added native model architecture support for Spark‑X2.5 (Spark2_5ForCausalLM) in [llama.cpp](https://github.com/ggml-org/llama.cpp/releases/tag/b10829) .\n- [2026/09/04] 🚀 Released FP8 and INT8 quantized versions of Spark-X2.5-4B and Spark-X2.5-1.7B.\n- [2026/09/03] 🤝 Added deployment support for vLLM and SGLang on Ascend NPU.\n- [2026/09/02] 🚀 Added [AtomGit](https://ai.atomgit.com/collections/2095030878254981121) as a new distribution channel.\n- [2026/09/01] 🚀 Global launch of the Spark-X2.5 model series on [Hugging Face](https://huggingface.co/collections/XHToken/spark-x25) ,[ModelScope](https://www.modelscope.cn/collections/XHToken/Spark-X25) ,[Ollama](https://ollama.com/SparkLLM) ,[Modelers](https://modelers.cn/user/XHToken) , and[SCNet](https://www.scnet.cn/ui/aihub/models/XHToken/Spark-X2.5-4B) .\n\nThe Spark-X2.5-4B and Spark-X2.5-1.7B are available on the following platforms. Choose the most suitable download source for your region and environment:\n\n| Platform | Download | Description | \n|---|---|---|\n| Hugging Face | [Spark-X2.5 in Huggingface](https://huggingface.co/collections/XHToken/spark-x25) | Official Hugging Face model collection for Spark-X2.5 | \n| ModelScope | [Spark-X2.5 in ModelScope](https://www.modelscope.cn/collections/XHToken/Spark-X25) | Recommended download source for users in China | \n| Modelers | [Spark-X2.5 in Modelers](https://modelers.cn/user/XHToken) | Recommended download source for users with Ascend chips | \n| Ollama | [Spark-X2.5 in Ollama](https://ollama.com/SparkLLM) | Download and run the model locally with Ollama | \n| SCNet | [Spark-X2.5 in SCNet](https://www.scnet.cn/ui/aihub/models/XHToken/Spark-X2.5-4B) | Recommended download source for users with Hygon chips | \n| AtomGit | [Spark-X2.5 in AtomGit](https://ai.atomgit.com/collections/2095030878254981121) | Recommended download source for users in China | \n\nIf Hugging Face is slow or unavailable in your region, try ModelScope, Modelers, SCNet or AtomGit instead.\n\n| Benchmark | Spark‑X2.5‑4B | Spark‑X2.5‑1.7B | Qwen3.5‑9B | Qwen3.5‑4B | Qwen3.5‑2B | Gemma4‑12B | Gemma4‑E4B | Gemma4‑E2B | \n|---|---|---|---|---|---|---|---|---|\n| Agent |  |  |  |  |  |  |  |  | \n| BFCL‑V4 | 65.1 | 46.9 | **66.1*** | 50.3* | 43.6* | 37.4 | 36.9 | 30.2 | \n| τ²‑bench | 75.1 | 65.3 | 79.1* | **79.9*** | 48.8* | 69.0* | 42.2* | 24.5* | \n| τ³‑bench | **30.4** | 20.1 | 9.3 | 6.7 | 4.1 | 13.3 | 10.1 | 8.8 | \n| MCP‑Atlas | **54.6** | 23.4 | 47.4* | 40.8* | 14.8 | 30.5* | 15.0* | 12.6 | \n| MCP‑Mark | **14.2** | 2.3 | 13.4 | 12.5 | – | – | – | – | \n| Workspace Bench | **31.2** | 18.9 | 25.5 | 21.3 | 7.7 | – | – | – | \n| VitaBench2.0 | **25.2** | 8.3 | 15.6 | 18.2 | 5.2 | 12.4 | 4.8 | 4.4 | \n| BrowseComp | **40.9** | 29.7 | 8.3 | 14.3 | 3.1 | 10.0 | 8.3 | 3.7 | \n| Code |  |  |  |  |  |  |  |  | \n| SWE‑Bench Pro | **44.4** | 10.4 | 33.8* | 29.4* | 1.9 | 21.9* | 4.0* | – | \n| SWE‑Bench Verified | 41.6 | 28.3 | **53.1*** | 38.8* | 6.8 | 44.2* | 14.0* | – | \n| SWE‑Bench Multilingual | **53.3** | 23.3 | 43.3 | 27.7 | 5.0 | 32.5* | – | – | \n| SciCode | 34.7 | 18.2 | 32.7* | 24.0 | 6.0 | **39.8** | 27.5 | 20.5 | \n| Math |  |  |  |  |  |  |  |  | \n| Gaokao 2026 | 133.4 | 114.8 | **135.5** | 130.3 | 94.0 | 130.6 | 102.4 | 81.8 | \n| AIME 2026 | **90.7** | 69.4 | 88.2 | 83.0 | 30.8 | 82.1* | 42.5* | 37.5* | \n| HMMT Feb 2026 | **81.2** | 48.4 | 70.8 | 69.7 | 21.5 | 65.6 | 34.2 | 20.5 | \n| IMO‑AnswerBench | **74.2** | 45.4 | 69.8 | 68.5 | – | 57.2 | 26.9 | 22.6 | \n| General & Knowledge |  |  |  |  |  |  |  |  | \n| IFEval | 93.0 | 89.5 | 91.5* | 89.8* | 78.6* | **94.8** | 45.3 | 34.8 | \n| IFBench | **75.0** | 66.3 | 64.5 | 59.2 | 41.3* | 73.5* | 44.0* | 22.7 | \n| AA‑LCR | 56.3 | 24.3 | **63.0*** | 57.0* | 25.6* | 55.3* | 34.7 | 18.3 | \n| HLE | 12.3 | 6.3 | **14.3** | 8.6 | 2.1 | 13.1 | 3.9 | 2.5 | \n| GPQA | 67.4 | 43.8 | **77.2** | 67.2 | 44.6 | 72.8 | 54.5 | 43.8 | \n\n- * denotes reported results from publicly‑released model cards / papers and - denotes scores not yet available.\n- All evaluations are conducted in thinking mode. The recommended sampling parameters for Spark-X2.5 are temperature=1.0, top_p=0.95, and top_k=-1.\n- Gaokao 2026 consists of the five 2026 Chinese GAOKAO examinations (National I,National II, Beijing, Shanghai, Tianjin), each graded out of 150 points.\n\nThe examples below serve a local Spark-X2.5-4B checkpoint. Set `MODEL_PATH` to its absolute path before starting a container:\n\n```\nexport MODEL_PATH=/absolute/path/to/Spark-X2.5-4B\n```\n\nUse the pre-built image that tracks the Spark-X2.5 runtime:\n\n```\ndocker pull lmsysorg/sglang:nightly-dev-cu13-20260827-20621aa1\n# A3 daily build\nexport SGLANG_IMAGE=quay.io/ascend/sglang:main-cann9.0.0-a3\n\n# A2 daily build (use this instead on A2 hardware)\nexport SGLANG_IMAGE=quay.io/ascend/sglang:main-cann9.0.0-910b\n\ndocker pull \"$SGLANG_IMAGE\"\n```\n\nThe following commands start an OpenAI-compatible API server configured for a maximum context length of 1,048,576 tokens. This setting requires sufficient device memory; reduce `--context-length` when necessary.\n\n```\ndocker run --rm -it \\\n  --gpus '\"device=0\"' \\\n  --ipc=host \\\n  -p 30000:30000 \\\n  -v \"$MODEL_PATH\":/root/Spark-X2.5-4B:ro \\\n  lmsysorg/sglang:nightly-dev-cu13-20260827-20621aa1 \\\n  python -m sglang.launch_server \\\n    --model-path /root/Spark-X2.5-4B \\\n    --served-model-name spark2.5 \\\n    --tool-call-parser spark25 \\\n    --reasoning-parser qwen3 \\\n    --tp-size 1 \\\n    --mem-fraction-static 0.8 \\\n    --context-length 1048576 \\\n    --chat-template /root/Spark-X2.5-4B/chat_template.jinja \\\n    --host 0.0.0.0 \\\n    --port 30000\ndocker run -it --rm -e ASCEND_USE_FIA=1 --network=host --ipc=host --shm-size=16g \\\n    --device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \\\n    --device=/dev/davinci4 --device=/dev/davinci5 --device=/dev/davinci6 --device=/dev/davinci7 \\\n    --device=/dev/davinci8 --device=/dev/davinci9 --device=/dev/davinci10 --device=/dev/davinci11 \\\n    --device=/dev/davinci12 --device=/dev/davinci13 --device=/dev/davinci14 --device=/dev/davinci15 \\\n    --device=/dev/davinci_manager \\\n    --device=/dev/devmm_svm \\\n    --device=/dev/hisi_hdc \\\n    --volume /usr/local/sbin:/usr/local/sbin \\\n    --volume /usr/local/Ascend/driver:/usr/local/Ascend/driver \\\n    --volume /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \\\n    --volume /etc/ascend_install.info:/etc/ascend_install.info \\\n    --volume /var/queue_schedule:/var/queue_schedule \\\n    --volume ~/.cache/:/root/.cache/ \\\n    --volume \"$MODEL_PATH:/root/Spark-X2.5-4B:ro\" \\\n    --entrypoint=python \\\n    \"$SGLANG_IMAGE\" \\\n    -m sglang.launch_server \\\n      --model-path /root/Spark-X2.5-4B \\\n      --served-model-name spark2.5 \\\n      --tool-call-parser spark25 \\\n      --reasoning-parser qwen3 \\\n      --tp-size 1 \\\n      --mem-fraction-static 0.8 \\\n      --context-length 1048576 \\\n      --chat-template /root/Spark-X2.5-4B/chat_template.jinja \\\n      --host 0.0.0.0 \\\n      --port 30000\n```\n\nThinking is enabled by default by both the chat template and the Qwen3 reasoning parser. To disable thinking for a specific request, set `\"chat_template_kwargs\": {\"enable_thinking\": false}`.\n\n```\ncurl -s http://localhost:30000/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"spark2.5\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": \"安徽的省会在哪里？\"\n      }\n    ],\n    \"max_tokens\": 131072,\n    \"temperature\": 1,\n    \"top_k\": -1,\n    \"top_p\": 0.95,\n    \"repetition_penalty\": 1,\n    \"presence_penalty\": 0,\n    \"frequency_penalty\": 0\n  }'\n```\n\nvLLM provides an official Docker image for NVIDIA GPU deployment:\n\n```\ndocker run --rm --gpus all \\\n  --ipc=host \\\n  -p 30000:30000 \\\n  -v \"$MODEL_PATH:/models/Spark-X2.5-4B:ro\" \\\n  vllm/vllm-openai:latest \\\n  --model /models/Spark-X2.5-4B \\\n  --port 30000 \\\n  --trust-remote-code \\\n  --served-model-name spark25 \\\n  --tensor-parallel-size 1 \\\n  --gpu-memory-utilization 0.7 \\\n  --enable-prefix-caching \\\n  --chat-template /models/Spark-X2.5-4B/chat_template.jinja\n```\n\nFor Ascend NPUs, choose an official image for the fastest setup.\n\n```\nexport IMAGE=quay.io/ascend/vllm-ascend:nightly-main\ndocker pull \"$IMAGE\"\n\nexport DEVICE=/dev/davinci0\nexport MODEL_CACHE=\"${HOME}/.cache\"\n\nmkdir -p \"$MODEL_CACHE\"\n\ndocker run --rm \\\n    --name vllm-ascend \\\n    --shm-size=1g \\\n    --device \"$DEVICE\" \\\n    --device /dev/davinci_manager \\\n    --device /dev/devmm_svm \\\n    --device /dev/hisi_hdc \\\n    -v /usr/local/dcmi:/usr/local/dcmi \\\n    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \\\n    -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \\\n    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \\\n    -v /etc/ascend_install.info:/etc/ascend_install.info \\\n    -v \"$MODEL_CACHE:/root/.cache\" \\\n    -p 8000:8000 \\\n    -it \"$IMAGE\" bash\nexport IMAGE=quay.io/ascend/vllm-ascend:nightly-main-a3\ndocker pull \"$IMAGE\"\n\nexport DEVICE0=/dev/davinci0\nexport DEVICE1=/dev/davinci1\nexport MODEL_CACHE=\"${HOME}/.cache\"\n\nmkdir -p \"$MODEL_CACHE\"\n\ndocker run --rm \\\n    --name vllm-ascend \\\n    --shm-size=1g \\\n    --device \"$DEVICE0\" \\\n    --device \"$DEVICE1\" \\\n    --device /dev/davinci_manager \\\n    --device /dev/devmm_svm \\\n    --device /dev/hisi_hdc \\\n    -v /usr/local/dcmi:/usr/local/dcmi \\\n    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \\\n    -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \\\n    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \\\n    -v /etc/ascend_install.info:/etc/ascend_install.info \\\n    -v \"$MODEL_CACHE:/root/.cache\" \\\n    -p 8000:8000 \\\n    -it \"$IMAGE\" bash\nexport IMAGE=quay.io/ascend/vllm-ascend:nightly-main-a5\ndocker pull \"$IMAGE\"\n\nexport MODEL_CACHE=\"${HOME}/.cache\"\n\nmkdir -p \"$MODEL_CACHE\"\n\ndocker run --rm \\\n    --name vllm-ascend \\\n    --net=host \\\n    --shm-size=1g \\\n    --device /dev/davinci0 \\\n    --device /dev/davinci_manager \\\n    --device /dev/devmm_svm \\\n    --device /dev/hisi_hdc \\\n    -v /usr/local/dcmi:/usr/local/dcmi \\\n    -v /usr/local/Ascend/driver/tools/hccn_tool:/usr/local/Ascend/driver/tools/hccn_tool \\\n    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \\\n    -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \\\n    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \\\n    -v /etc/ascend_install.info:/etc/ascend_install.info \\\n    -v \"$MODEL_CACHE:/root/.cache\" \\\n    -it \"$IMAGE\" bash\n```\n\nInstall the Spark plugin inside the container:\n\n```\npip install uv\nuv venv ~/spark2_5\nsource ~/spark2_5/bin/activate\ngit clone https://github.com/XHToken/Spark-plugin.git\ncd ./Spark-plugin\nuv pip install .\nvllm serve \"/models/Spark-X2.5-4B\" \\\n --port \"30000\" \\\n --trust-remote-code \\\n --served-model-name spark25 \\\n --tensor-parallel-size 1 \\\n --gpu-memory-utilization 0.7 \\\n --enable-prefix-caching \\\n --chat-template /models/Spark-X2.5-4B/chat_template.jinja\ncurl -s http://127.0.0.1:30000/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"spark25\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"安徽的省会在哪里？\"}],\n    \"temperature\": 1.0, \n    \"top_k\": -1,\n    \"top_p\": 0.95\n  }'\n```\n\nSpark-MLX-LLM runs the original Spark-X2.5 Hugging Face checkpoints locally. It supports Apple silicon GPU, Linux CPU, and NVIDIA CUDA on Linux. No GGUF conversion is required.\n\n```\ngit clone https://github.com/XHToken/Spark-MLX-LLM.git\ncd Spark-MLX-LLM\n\npython3 -m venv .venv\nsource .venv/bin/activate\n\n# Apple silicon\npython -m pip install -e .\n# Linux CPU\npython -m pip install -e '.[cpu]'\n# Linux with CUDA 12\npython -m pip install -e '.[cuda12]' \n# Linux with CUDA 13\npython -m pip install -e '.[cuda13]'\nspark-mlx-generate \\\n  --device gpu \\\n  --dtype bfloat16 \\\n  --model XHToken/Spark-X2.5-1.7B \\\n  --prompt \"安徽的省会在哪里？\" \\\n  --max-tokens 512 \\\n  --temp 0\n```\n\n1. \nDownload and install Ollama from [ollama.com](https://ollama.com/download) (v0.34.1 or later).\n2. \nRun the model:\n\n```\nollama run SparkLLM/Spark-X2.5-1.7B\n```\n\n1. \nDownload and install LM Studio from [lmstudio.ai](https://lmstudio.ai/download) (0.4.0 or later).\n2. \nSearch for \"Spark-X2.5\" in LM Studio and download the model.\n3. \nLoad the model and start chatting.\n\n```\n# List available models\nlms ls\n\n# Run chat with Spark-X2.5\nlms chat spark-x2.5\n```\n\nNote\n\nThe latest Unsloth Studio supports native Spark-X2.5 GGUF inference.\n\nWe recommend using [Llama-Factory](https://github.com/XHToken/LlamaFactory) to fine-tune the model.\n\nThe Spark-X2.5 model series is licensed under the [Apache 2.0 License](https://github.com/XHToken/Spark-X2.5/blob/main/LICENSE).\n\nIf you find our work helpful, feel free to give us a cite.\n\n```\n@misc{sparkx2.5,\n    title  = {Spark-X2.5 4B&1.7B: Pushing the Limits of Agentic Capabilities in On-Device Models},\n    author = {SparkLLM Team},\n    year   = {2026}\n}\n```\n\n", "url": "https://wpnews.pro/news/spark-x2-5", "canonical_source": "https://github.com/XHToken/Spark-X2.5", "published_at": "2026-09-30 11:05:23+00:00", "updated_at": "2026-09-30 11:19:58.978117+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-infrastructure", "ai-agents"], "entities": ["XHToken", "Spark-X2.5", "Spark-X2.5-4B", "Spark-X2.5-1.7B", "Huawei Ascend", "Hugging Face", "llama.cpp", "Ollama"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/spark-x2-5", "markdown": "https://wpnews.pro/news/spark-x2-5.md", "text": "https://wpnews.pro/news/spark-x2-5.txt", "jsonld": "https://wpnews.pro/news/spark-x2-5.jsonld"}}