Ling 3.0 tiny MXFP4 MOE needs about 10.5 GB of memory at MXFP4_MOE (a 5.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 4.9 GB (MXFP4_MOE) to 9.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.
Ling 3.0 tiny MXFP4 MOE is a 7.89B-parameter Ling model in GGUF format, quantized by noctrex. Its trained context length is 128K tokens. The repository has 4 quant files, from 4.9 GB (MXFP4_MOE) to 9.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 4.9 GB | 9.8 GB | Too big | Get file → | |
| MXFP4_MOE | 5.6 GB | 10.5 GB | Too big | Get file → | |
| MXFP4_MOE | 5.6 GB | 10.5 GB | Too big | Get file → | |
| — | 9.3 GB | 14.2 GB | Too big | Get file → |
What GPU do you need for Ling 3.0 tiny MXFP4 MOE?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is MXFP4_MOE (5.6 GB file, about 10.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 14.2 GB in use).
Which Ling 3.0 tiny MXFP4 MOE quant should you choose?
MXFP4_MOE (5.6 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is MXFP4_MOE at 4.9 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 Ling 3.0 tiny MXFP4 MOE
How much VRAM does Ling 3.0 tiny MXFP4 MOE need?
About 10.5 GB at MXFP4_MOE with an 8K context window. That is the 5.6 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 Ling 3.0 tiny MXFP4 MOE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling 3.0 tiny MXFP4 MOE GGUF?
It depends on the quant: MXFP4_MOE is 4.9 GB, MXFP4_MOE is 5.6 GB, MXFP4_MOE is 5.6 GB, file is 9.3 GB.
What context length does Ling 3.0 tiny MXFP4 MOE support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.4 GB at 8K and 17.7 GB at 32K.
Where can I download Ling 3.0 tiny MXFP4 MOE GGUF?
The files are on Hugging Face in the noctrex/Ling-3.0-tiny-MXFP4_MOE-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 Ling 3.0 tiny MXFP4 MOE use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.