Spark X2.5 4B needs about 4.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.6 GB (Q4_K_M) to 8.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Spark X2.5 4B – compact, general‑purpose LLM with 1M‑token context
Spark X2.5 4B is a 4.1B‑parameter language model built on the spark2_5 architecture. It supports a native context window of up to 1M tokens and is trained for a wide range of tasks such as conversation, coding, and agent workflows. The model is released under Apache‑2.0 and is compatible with llama.cpp, vLLM, SGLang, and other inference frameworks.
Good at
- Large‑context conversation
- Coding and agentic tasks
- Multilingual support over 200 languages
Limits
- No vision support
- Requires native spark2_5 support in llama.cpp v0.10828 or later
- Large memory for 1M context
Best for
- Developers building chatbots with long context
- Researchers testing agentic workflows
- Fine‑tuning for specialized coding tasks
Who it’s for. The model is suitable for developers and researchers who need a compact, efficient LLM that can handle very long contexts and a broad set of languages. It is ideal for those deploying on NVIDIA, Huawei, or other supported hardware using llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q8_0 | 4.4 GB | 6.1 GB | Fits | Get file → | |
| — | 8.2 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.6 GB file, ~4.3 GB RAM at 8 k context). For 12 GB VRAM, Q8_0 (4.38 GB file, ~6.1 GB RAM). The unknown quant requires ~9.9 GB RAM and 8.23 GB file, suitable only for larger GPUs.
What GPU do you need for 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.6 GB file, about 4.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.2 GB file, about 9.9 GB in use).
Which Spark X2.5 4B quant should you choose?
Q4_K_M is the usual starting point for Spark X2.5 4B: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Spark X2.5 4B
How much VRAM does Spark X2.5 4B need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Spark X2.5 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.4 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Spark X2.5 4B GGUF?
It depends on the quant: Q4_K_M is 2.6 GB, Q8_0 is 4.4 GB, file is 8.2 GB.
What context length does 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 Spark X2.5 4B GGUF?
The files are on Hugging Face in the XHToken/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 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 Spark X2.5 4B on 8 GB VRAM?
Yes, with the Q4_K_M quant the model file is 2.6 GB and requires about 4.3 GB of RAM at 8 k context.
Does the model support image inputs?
No, Spark X2.5 4B does not support vision or multimodal inputs.
What license applies to this model?
The model is released under the Apache License 2.0.