jayyun98/Ling-3.0-Tiny-DSpark needs about 0.9 GB of memory at Q4_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.1 GB (TQ1_0) to 0.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.
Ling-3.0-Tiny-DSpark: a 274M‑parameter DSpark draft model
Ling-3.0-Tiny-DSpark is a 274 billion‑parameter model in the Ling family, built on the dflash architecture. It is an experimental draft released by Jay Yun and quantized by StefanoBalocco. The model supports a maximum context length of 131072 tokens.
Good at
- Experimental DSpark draft
- Small model size
- Low VRAM requirement
Limits
- No official production certification
- No vision support
- License type is other
Best for
- Research prototypes
- Low‑resource inference
- Speculative decoding experiments
Who it’s for. Researchers and developers exploring DSpark speculative decoding. The model is not intended for production use and requires a compatible Ling‑3.0‑Tiny target model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| TQ2_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q2_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q5_0 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 1.0 GB | Fits | Get file → | |
| BF16 | 0.6 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, the TQ1_0 or TQ2_0 variants (0.06 GB and 0.08 GB) are suitable, each estimating 0.8 GB memory at 8 k context. If more VRAM is available, Q4_0 or Q5_0 (0.16 GB and 0.2 GB) provide slightly higher quality. BF16 (0.55 GB) requires more memory but preserves full precision.
What GPU do you need for jayyun98/Ling-3.0-Tiny-DSpark?
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 BF16 (0.6 GB file, about 1.3 GB in use).
Which jayyun98/Ling-3.0-Tiny-DSpark quant should you choose?
Q4_0 (0.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is TQ1_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jayyun98/Ling-3.0-Tiny-DSpark
How much VRAM does jayyun98/Ling-3.0-Tiny-DSpark need?
About 0.9 GB at Q4_0 with an 8K context window. That is the 0.2 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 jayyun98/Ling-3.0-Tiny-DSpark on an 8 GB GPU?
Yes, with BF16: the 0.6 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jayyun98/Ling-3.0-Tiny-DSpark GGUF?
It depends on the quant: TQ1_0 is 0.1 GB, TQ2_0 is 0.1 GB, Q2_0 is 0.1 GB, Q4_0 is 0.2 GB, Q5_0 is 0.2 GB, Q8_0 is 0.3 GB and 1 more.
What context length does jayyun98/Ling-3.0-Tiny-DSpark support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.
Where can I download jayyun98/Ling-3.0-Tiny-DSpark GGUF?
The files are on Hugging Face in the StefanoBalocco/Ling-3.0-Tiny-DSpark-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 jayyun98/Ling-3.0-Tiny-DSpark use?
Hugging Face lists the license as other. 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 Ling-3.0-Tiny-DSpark on 8 GB VRAM?
Yes, the TQ1_0 and TQ2_0 quantizations use about 0.8 GB memory at 8 k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
No, Ling-3.0-Tiny-DSpark is a text‑only model with no vision capabilities.
Is this model suitable for production?
No, it is an experimental draft and not intended for production deployment.