LI

Ling-3.0-tiny-base-30T

LingGGUF by FriskyFennecUpdated 2026-09-10
Download on Hugging Face
Parameters8.2B
Context8K
Layers25
Architecturebailingmoe3
Smallest quant3.6 GB
Quick answer

Ling-3.0-tiny-base-30T needs about 10.1 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 3.6 GB (Q3_K_S) to 16.4 GB (BF16).

Ling-3.0-tiny-base-30T – 8.2B parameter MoE model with 8192 token context

Ling-3.0-tiny-base-30T is an 8.2B parameter language model built on a highly sparse MoE architecture. It supports a 8192 token context and is released under the MIT license. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Sparse MoE for broad capabilities
  • Hybrid linear attention for long‑context
  • Efficient inference with llama.cpp

Limits

  • No vision support
  • Requires 8.8–21.6 GB VRAM for full context
  • Only text completion use cases

Best for

  • Text completion in low‑memory environments
  • Fine‑tuning on custom corpora
  • Research on MoE architectures

Who it’s for. Researchers and developers who need a lightweight, text‑only foundation model for experimentation or deployment on modest hardware. The model is suitable for those who prefer open‑source licensing and can work within the 8192 token context limit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.6 GB 8.8 GB
Too big Get file →
Q3_K_M4.0 GB 9.1 GB
Too big Get file →
Q3_K_L4.3 GB 9.4 GB
Too big Get file →
Q4_04.7 GB 9.8 GB
Too big Get file →
Q4_K_S4.7 GB 9.8 GB
Too big Get file →
Q4_K_M5.0 GB 10.1 GB
Too big Get file →
Q5_05.7 GB 10.8 GB
Too big Get file →
Q5_K_S5.7 GB 10.8 GB
Too big Get file →
Q5_K_M5.9 GB 11.0 GB
Too big Get file →
Q6_K6.8 GB 11.9 GB
Too big Get file →
Q8_08.7 GB 13.9 GB
Too big Get file →
BF1616.4 GB 21.6 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_S (3.65 GB file, 8.8 GB memory). For 12 GB VRAM, Q4_K_M (5.03 GB file, 10.1 GB memory) is a good balance. If 16 GB VRAM is available, Q5_K_M (5.87 GB file, 11 GB memory) offers higher precision.

What GPU do you need for Ling-3.0-tiny-base-30T?

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 Q6_K (6.8 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 21.6 GB in use).

Which Ling-3.0-tiny-base-30T quant should you choose?

Q4_K_M is the usual starting point for Ling-3.0-tiny-base-30T: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.7 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 Q3_K_S at 3.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebailingmoe3
Parameters8.2B (approximate, mixture of experts)
Layers25
Trained context8,192 tokens
KV cache (fp16)550 KB per token

Source

Quantized byFriskyFennec
FamilyLing
Licensemit
Downloads (HF)2,255
Last updated2026-09-10

Frequently asked questions about Ling-3.0-tiny-base-30T

How much VRAM does Ling-3.0-tiny-base-30T need?

About 10.1 GB at Q4_K_M with an 8K context window. That is the 5.0 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-base-30T on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ling-3.0-tiny-base-30T GGUF?

It depends on the quant: Q3_K_S is 3.6 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB, Q4_K_M is 5.0 GB and 6 more.

What context length does Ling-3.0-tiny-base-30T support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.6 GB at 8K and 4.6 GB at 8K.

Where can I download Ling-3.0-tiny-base-30T GGUF?

The files are on Hugging Face in the FriskyFennec/Ling-3.0-tiny-base-30T-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-base-30T 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-base-30T on 8 GB VRAM?

Yes, the Q3_K_S quantization uses 8.8 GB memory at 8 k context, which fits within 8 GB VRAM with some headroom.

Does this model support image inputs?

No, Ling-3.0-tiny-base-30T is a text‑only model and has no vision capabilities.

What context length can I use?

The GGUF variant supports 8192 tokens; a full 256K context variant is available separately.

Other GGUFs of Ling-3.0-tiny-base-30T

Similar models

Browse all →

More from FriskyFennec

All by FriskyFennec →

More Ling models

All Ling →

Other small models

All small models →