Sakura Spark X2.5 4B needs about 4.1 GB of memory at its main file (a 2.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.8 GB to 2.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Sakura Spark X2.5 4B – compact general‑purpose LLM with 1M‑token context
Sakura Spark X2.5 4B is a 4.11B‑parameter model built on the spark2_5 architecture. It supports reasoning and tool use and offers a native 1M‑token context window. The model is released under Apache‑2.0 and is compatible with llama.cpp, vLLM, SGLang, MLX and other inference frameworks.
Good at
- Reasoning
- Tool use
- Long‑context conversation
Limits
- No vision support
- Large memory requirement for full context
- No official quantization
Best for
- Chatbots needing long context
- Agent workflows with tool integration
- Coding assistance
Who it’s for. Developers and researchers who need a compact model capable of handling up to 1M tokens and integrating with agent harnesses. The model is suitable for deployment on GPUs with sufficient VRAM and for use in inference frameworks that support llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.8 GB | 3.5 GB | Fits | Get file → | |
| — | 2.4 GB | 4.1 GB | Fits | Get file → | |
| — | 2.7 GB | 4.4 GB | Fits | Get file → |
For 8 GB VRAM use the 1.83 GB file (est. 3.5 GB memory at 8 k context). For 12 GB VRAM use the 2.42 GB file (est. 4.1 GB memory). For 16 GB VRAM use the 2.65 GB file (est. 4.4 GB memory). Memory estimates are approximate.
What GPU do you need for Sakura Spark X2.5 4B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (1.8 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (2.7 GB file, about 4.4 GB in use).
Which Sakura Spark X2.5 4B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 1.8 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura Spark X2.5 4B
How much VRAM does Sakura Spark X2.5 4B need?
About 4.1 GB at its main file with an 8K context window. That is the 2.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Sakura Spark X2.5 4B on an 8 GB GPU?
Yes, with the smaller files: the 2.7 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura Spark X2.5 4B GGUF?
It depends on the quant: file is 1.8 GB, file is 2.4 GB, file is 2.7 GB.
What context length does Sakura Spark X2.5 4B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Sakura Spark X2.5 4B GGUF?
The files are on Hugging Face in the webmp3/Sakura-Spark-X2.5-4B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura Spark X2.5 4B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Sakura Spark X2.5 4B on 8 GB VRAM?
Yes, the 1.83 GB GGUF file requires about 3.5 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.