Ling 3.0 Tiny needs about 10.0 GB of memory at MXFP4 (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 5.1 GB (MXFP4) to 6.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.
Ling 3.0 Tiny – a lightweight hybrid reasoning MoE model
Ling 3.0 Tiny is a 7.89B parameter model with only 1.3B activated per token. It supports reasoning and tool use and is optimized for local and edge deployment. The model runs on llama.cpp with antirez recipe quants.
Good at
- Reasoning
- Tool use
- Low inference cost
Limits
- No vision support
- Requires 8K context for full capability
- MIT license only
Best for
- Local reasoning tasks
- Agentic workflows
- Edge deployment
Who it’s for. Developers needing a small, efficient model for reasoning and agentic tasks on limited hardware. It is suitable for local inference on GPUs or CPUs with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 5.1 GB | 10.0 GB | Too big | Get file → | |
| Q5_K_M | 6.9 GB | 11.8 GB | Too big | Get file → |
For 8GB VRAM, use the MXFP4 quant (5.09 GB file, ~10 GB memory at 8K context). For 12GB VRAM, use Q5_K_M (6.9 GB file, ~11.8 GB memory at 8K context).
What GPU do you need for Ling 3.0 Tiny?
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 Q5_K_M (6.9 GB file, about 11.8 GB in use).
Which Ling 3.0 Tiny quant should you choose?
MXFP4 (5.1 GB) is the middle option in this repository. 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
How much VRAM does Ling 3.0 Tiny need?
About 10.0 GB at MXFP4 with an 8K context window. That is the 5.1 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling 3.0 Tiny GGUF?
It depends on the quant: MXFP4 is 5.1 GB, Q5_K_M is 6.9 GB.
What context length does Ling 3.0 Tiny 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 GGUF?
The files are on Hugging Face in the Ninnix96/Ling-3.0-tiny-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 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.
Can I run Ling 3.0 Tiny on 8GB VRAM?
Yes, the MXFP4 quant is 5.09 GB and requires about 10 GB memory at 8K context, which fits 8GB VRAM with some headroom.
Does Ling 3.0 Tiny support vision?
No, the model has no vision capabilities.