Ling 3.0 Tiny needs about 9.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 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 – a lightweight hybrid reasoning MoE model
Ling 3.0 Tiny is an 8.2‑billion‑parameter model with only 1.3 B active parameters per token. It uses a 3:1 KDA–MLA architecture and a sparse MoE FFN with 128 experts. The model supports long‑context reasoning and agentic tasks while remaining efficient for local deployment.
Good at
- Hybrid reasoning and agentic tasks
- Long‑context modeling up to 131 072 tokens
- Efficient inference on edge hardware
Limits
- Requires 8 K context for memory estimates
- No vision support
- License is MIT – no restrictions on use
Best for
- Local reasoning agents
- Edge‑device inference
- Low‑cost multi‑step reasoning
Who it’s for. Developers and researchers who need a small, efficient model for reasoning and agentic workloads on local or edge devices. The model is suitable for applications that require long‑context support without large GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 7.8 GB | Tight | Get file → | |
| Q2_K | 3.0 GB | 7.9 GB | Tight | Get file → | |
| Q2_K_L | 3.2 GB | 8.2 GB | Too big | Get file → | |
| IQ3_XXS | 3.5 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 3.6 GB | 8.6 GB | Too big | Get file → | |
| IQ3_XS | 3.8 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 3.8 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_L | 3.9 GB | 8.8 GB | Too big | Get file → | |
| IQ3_M | 3.9 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_XL | 4.1 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 4.4 GB | 9.3 GB | Too big | Get file → | |
| IQ4_NL | 4.6 GB | 9.5 GB | Too big | Get file → | |
| Q4_0 | 4.6 GB | 9.6 GB | Too big | Get file → | |
| Q4_K_S | 4.8 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_M | 4.9 GB | 9.8 GB | Too big | Get file → | |
| Q4_1 | 5.1 GB | 10.0 GB | Too big | Get file → | |
| Q4_K_L | 5.1 GB | 10.0 GB | Too big | Get file → | |
| Q5_K_S | 5.5 GB | 10.5 GB | Too big | Get file → | |
| Q5_K_M | 5.7 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_L | 5.9 GB | 10.8 GB | Too big | Get file → | |
| Q6_K | 6.8 GB | 11.8 GB | Too big | Get file → | |
| Q6_K_L | 7.0 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 8.4 GB | 13.3 GB | Too big | Get file → | |
| BF16 | 15.8 GB | 20.7 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (4.92 GB) or Q4_K_L (5.10 GB) are suitable, providing a balance of size and performance. If 16 GB VRAM is available, Q5_K_M (5.72 GB) or Q6_K (6.84 GB) offer higher quality. The smallest quant, IQ2_M (2.83 GB), fits on 4 GB VRAM but with reduced accuracy.
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: the best quant that fits is the main file (0.0 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (3.0 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K_L (7.0 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 13.3 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 quant should you choose?
Q4_K_M is the usual starting point for Ling 3.0 Tiny: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.4 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 Ling 3.0 Tiny
How much VRAM does Ling 3.0 Tiny need?
About 9.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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?
Yes, with Q2_K: the 3.0 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ling 3.0 Tiny GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 2.8 GB, Q2_K is 3.0 GB, Q2_K_L is 3.2 GB, IQ3_XXS is 3.5 GB, Q3_K_S is 3.6 GB and 19 more.
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 bartowski/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 8 GB VRAM?
Yes, Q4_K_M (4.92 GB) or Q4_K_L (5.10 GB) fit within 8 GB VRAM, with approximate memory usage of 9.8–10 GB at 8K context.
What is the maximum context length for this model?
The model was trained with 131 072 tokens and supports that full context length in inference.
Does Ling 3.0 Tiny support vision tasks?
No, the model only supports text input and has no vision capabilities.