Ling 3.0 tiny abliterated APEX needs about 10.7 GB of memory at its main file (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.4 GB to 15.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.
Ling‑3.0‑tiny abliterated APEX: 7.9B MoE model with 1.3B active parameters
Ling‑3.0‑tiny abliterated APEX is a 7.9B parameter hybrid‑linear MoE model. It activates only 1.3B parameters per token, enabling efficient reasoning and agentic tasks on local hardware. The model supports long‑context up to 131072 tokens and is released under the MIT license.
Good at
- Hybrid reasoning and multi‑step thinking
- Efficient local deployment on 6‑8 GB GPUs
- Strong performance in coding and math tasks
Limits
- No vision support
- Requires 8 K context for full memory estimate
- Only available in GGUF format
Best for
- Local reasoning agents
- Edge‑device code assistants
- Long‑context chat on 8 GB GPUs
Who it’s for. Developers and researchers needing a lightweight MoE model for local inference. The model is suitable for edge devices and small‑GPU setups that require advanced reasoning without large memory footprints.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.4 GB | 8.3 GB | Too big | Get file → | |
| — | 4.0 GB | 8.9 GB | Too big | Get file → | |
| — | 5.8 GB | 10.7 GB | Too big | Get file → | |
| — | 6.0 GB | 10.9 GB | Too big | Get file → | |
| BF16 | 15.8 GB | 20.7 GB | Too big | Get file → |
For 6 GB GPUs, use the *-APEX‑Mini.gguf (3.41 GB) or *-APEX‑Compact.gguf (3.99 GB) files; they require about 8–9 GB VRAM at 8 K context. For 8 GB GPUs, the *-APEX‑Balanced.gguf (5.96 GB) or *-APEX‑I‑Quality.gguf (5.77 GB) provide higher accuracy. BF16 is available for larger GPUs.
What GPU do you need for Ling 3.0 tiny abliterated APEX?
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 the main file (6.0 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (6.0 GB file, about 10.9 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.8 GB file, about 20.7 GB in use).
Which Ling 3.0 tiny abliterated APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 3.4 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 Ling 3.0 tiny abliterated APEX
How much VRAM does Ling 3.0 tiny abliterated APEX need?
About 10.7 GB at its main file with an 8K context window. That is the 5.8 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 abliterated APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling 3.0 tiny abliterated APEX GGUF?
It depends on the quant: file is 3.4 GB, file is 4.0 GB, file is 5.8 GB, file is 6.0 GB, BF16 is 15.8 GB.
What context length does Ling 3.0 tiny abliterated APEX 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 abliterated APEX GGUF?
The files are on Hugging Face in the SC117/Ling-3.0-tiny-abliterated-APEX-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 abliterated APEX 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 abliterated APEX on 8 GB VRAM?
Yes, the *-APEX‑Compact.gguf (3.99 GB) or *-APEX‑Balanced.gguf (5.96 GB) files fit within 8 GB VRAM with an 8 K context length.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license does the model use?
The model is released under the MIT license.