Spark-X2.6-4B 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 34 quants, from 0.0 GB to 8.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Spark-X2.6-4B – compact 4.11B parameter model for on‑device agents
Spark-X2.6-4B is a 4.11B parameter language model built on the spark2_5 architecture. It supports reasoning and tool usage and is optimized for on‑device deployment with a 1,048,576 token context window. The model is released under the Apache‑2.0 license.
Good at
- Reasoning
- Tool usage
- On‑device agent tasks
Limits
- No vision support
- Large VRAM requirement for higher precision
- Requires 8‑k context for memory estimates
Best for
- Embedded agent applications
- Code generation on edge devices
- Interactive reasoning tasks
Who it’s for. Developers building lightweight agents that run locally on devices with limited memory. The model is suitable for applications needing reasoning and tool integration without relying on cloud inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.5 GB | Fits | Get file → | |
| Q2_K_M | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q2_K_L | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_S | 2.0 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.2 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.4 GB | 4.1 GB | Fits | Get file → | |
| IQ4_NL | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_L | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q4_1 | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q5_0 | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_0 | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_1 | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_L | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_1 | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q6_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q6_K_L | 3.5 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.4 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 6.5 GB | 8.2 GB | Too big | Get file → | |
| F16 | 6.5 GB | 8.2 GB | Too big | Get file → | |
| BF16 | 8.2 GB | 9.9 GB | Too big | Get file → | |
| F16 | 8.2 GB | 9.9 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (file size 2.64 GB, estimated 4.3 GB memory at 8‑k context). If 4‑GB VRAM is available, Q2_K_S (1.72 GB, 3.4 GB memory) is a good choice. For maximum precision on 12‑GB VRAM, Q8_0 (4.38 GB, 6.1 GB memory) is recommended.
What GPU do you need for Spark-X2.6-4B?
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 Q3_K_L (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (3.5 GB file, about 5.2 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 BF16 (8.2 GB file, about 9.9 GB in use).
Which Spark-X2.6-4B quant should you choose?
Q4_K_M is the usual starting point for Spark-X2.6-4B: 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.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Spark-X2.6-4B
How much VRAM does Spark-X2.6-4B 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-X2.6-4B 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-X2.6-4B GGUF?
It depends on the quant: file is 0.0 GB, Q2_K_S is 1.7 GB, IQ3_XXS is 1.8 GB, Q2_K_M is 1.8 GB, IQ3_XS is 1.9 GB, Q2_K_L is 1.9 GB and 28 more.
What context length does Spark-X2.6-4B 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-X2.6-4B GGUF?
The files are on Hugging Face in the Mungert/Spark-X2.6-4B-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-X2.6-4B 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-X2.6-4B on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires approximately 4.3 GB of VRAM at 8‑k context.
Does Spark-X2.6-4B support vision tasks?
No, the model does not include vision capabilities.
What license applies to Spark-X2.6-4B?
The model is released under the Apache‑2.0 license.