--- title: Spark-X2.6-4B-OptiQ-4bit canonical_url: "https://www.modelscope.cn/models/mlx-community/Spark-X2.6-4B-OptiQ-4bit" md_url: "https://www.modelscope.cn/models/mlx-community/Spark-X2.6-4B-OptiQ-4bit.md" repository: mlx-community/Spark-X2.6-4B-OptiQ-4bit last_updated: 2026-10-24 license: apache-2.0 pipeline_tag: text-generation tasks: - text-generation model_type: - spark2_5 architectures: - Spark2_5ForCausalLM base_model: - XHToken/Spark-X2.6-4B base_model_relation: quantized parameters: 824.4M tensor_type: - BF16 - U32 library_name: - mlx - safetensors - pytorch frameworks: - pytorch language: - en - zh downloads: 48 stars: 0 tags: - mlx - quantized - mixed-precision - 4bit - 8bit - optiq - apple-silicon - text-generation - spark2_5 - long-context --- # Spark-X2.6-4B-OptiQ-4bit > Spark-X2.6-4B-OptiQ-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Spark-X2.6-4B-OptiQ-4bit mlx-community/Spark-X2.6-4B-OptiQ-4bit 是 ModelScope 魔搭社区上的 824.4M 参数text-generation模型，采用 apache-2.0 许可，基于 XHToken/Spark-X2.6-4B 构建。 - **Repository**: mlx-community/Spark-X2.6-4B-OptiQ-4bit - **License**: apache-2.0 - **Tasks**: text-generation - **Parameters**: 824.4M - **Base model**: XHToken/Spark-X2.6-4B - **Tags**: mlx, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, text-generation, spark2_5, long-context - **Downloads**: 48 - **Stars**: 0 - **Last updated**: 2026-10-24 Source: https://www.modelscope.cn/models/mlx-community/Spark-X2.6-4B-OptiQ-4bit --- # mlx-community/Spark-X2.6-4B-OptiQ-4bit > **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. [Try the Lab](https://mlx-optiq.com/docs/lab/) · [All OptiQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/) A mixed-precision MLX quant of [XHToken/Spark-X2.6-4B](https://huggingface.co/XHToken/Spark-X2.6-4B), the on-device agent model that follows Spark-X2.5 with improved post-training for coding, tool use, long context and reasoning. 2.8 GB on disk, down from 7.7 GB bf16. See the [original card](https://huggingface.co/XHToken/Spark-X2.6-4B) for what the model is trained to do and how XHToken evaluates it. Spark is a new architecture for MLX, and mlx-optiq adds support for it, so **`import optiq` before `mlx_lm.load`**: stock mlx-lm does not know the `spark2_5` model type. ## What it is | Property | Value | |---|---| | Base | XHToken/Spark-X2.6-4B (same `spark2_5` architecture as Spark-X2.5-4B) | | Layers | 108 at 8-bit, 109 at 4-bit (217 total) | | Group size | 64 | | KV cache | `kv_config.json` included (mixed-precision KV for `optiq serve --kv-config`) | | On disk | 2.8 GB | Following `llama.cpp`'s naming for mixed quants, the "4bit" label denotes the predominant precision, not the weighted average. ## How the bit-widths were chosen The per-layer allocation was not measured on this model. It was transferred from [mlx-community/Spark-X2.5-4B-OptiQ-4bit](https://huggingface.co/mlx-community/Spark-X2.5-4B-OptiQ-4bit), whose allocation came from a KL-divergence sensitivity sweep over a [six-domain calibration mix](https://mlx-optiq.com/blog/calibration-mix). Spark-X2.6 keeps exactly the same architecture and modeling code as X2.5, and all **217 tensors matched with none unmatched**. ## Checked after conversion Run through this quant and its bf16 parent on Apple Silicon with greedy decoding: | Prompt | This quant | bf16 parent | |---|---|---| | 240 km in 3 h, average speed with steps | 80 km/h, same three steps | 80 km/h | | Capital of Australia, and why not Sydney | Canberra, a planned federal capital | Canberra, a planned federal capital | | `is_palindrome(s)` ignoring case and non-alphanumerics | correct function | correct function | | Author and year of *Pride and Prejudice* | Jane Austen, 1813 | Jane Austen, 1813 | | Call `get_weather` for Paris, JSON only | `{"tool_name": "get_weather", "params": {"location": "Paris"}}` | same call, `city` as the key | | 240 km in 3 h, thinking on | short think, then 80 km/h | same think and answer | | 17 × 23, number only | thinking off: **491** (wrong); thinking on: 391 | 391 both ways | The one miss is bare mental arithmetic with thinking off, where the quant answers in a single token with no working; the Spark-X2.5 quant makes the same slip. With thinking on, the default, it gets it right. ## Usage ```bash pip install mlx-optiq # brings mlx-lm and the spark2_5 architecture ``` ```python import optiq # registers spark2_5 with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/Spark-X2.6-4B-OptiQ-4bit") prompt = tokenizer.apply_chat_template( [{"role": "user", "content": "Explain quantum computing in simple terms."}], tokenize=False, add_generation_prompt=True, enable_thinking=False) print(generate(model, tokenizer, prompt=prompt, max_tokens=300)) ``` Serving, with the mixed-precision KV cache, tool calling and the OpenAI, Responses and Anthropic Messages APIs: ```bash optiq serve --model mlx-community/Spark-X2.6-4B-OptiQ-4bit --kv-config kv_config.json ``` ### Thinking and sampling Thinking is on by default. The chat template takes `reasoning_effort` of `high` (the default) or `low` to set how much it thinks, or `enable_thinking: false` to turn it off; pass them as `chat_template_kwargs` at the endpoint or as keywords to `apply_chat_template`. Through `optiq serve`, the standard `reasoning_effort: "none"` also turns it off. XHToken's sampling defaults, `temperature 1.0` and `top_p 0.95`, are bundled in `generation_config.json`. See the [Spark family guide](https://mlx-optiq.com/docs/spark) for serving flags and family caveats. ## Links - **Project website:** [mlx-optiq.com](https://mlx-optiq.com/) - **Spark family guide:** [mlx-optiq.com/docs/spark](https://mlx-optiq.com/docs/spark) - **PyPI:** [pypi.org/project/mlx-optiq](https://pypi.org/project/mlx-optiq/) - **Base model:** [XHToken/Spark-X2.6-4B](https://huggingface.co/XHToken/Spark-X2.6-4B)