LI

Ling Lite

LingGGUF by mradermacherUpdated 2025-04-03
Download on Hugging Face
Parameters16.8B
Context16K
Layers28
Architecturebailingmoe
Smallest quant5.4 GB
Quick answer

Ling Lite needs about 12.1 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 5.4 GB (IQ1_S) to 15.1 GB (Q6_K).

Ling Lite is a 16.8B-parameter Ling model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 24 quant files, from 5.4 GB (IQ1_S) to 15.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.4 GB 6.3 GB
Fits Get file →
IQ1_M5.6 GB 6.6 GB
Fits Get file →
IQ2_XXS6.1 GB 7.0 GB
Fits Get file →
IQ2_XS6.4 GB 7.4 GB
Tight Get file →
IQ2_S6.5 GB 7.4 GB
Tight Get file →
IQ2_M6.8 GB 7.8 GB
Tight Get file →
Q2_K6.9 GB 7.9 GB
Tight Get file →
Q2_K_S7.0 GB 7.9 GB
Tight Get file →
IQ3_XXS7.5 GB 8.4 GB
Too big Get file →
IQ3_XS7.6 GB 8.6 GB
Too big Get file →
Q3_K_S8.0 GB 9.0 GB
Too big Get file →
IQ3_S8.0 GB 9.0 GB
Too big Get file →
IQ3_M8.1 GB 9.1 GB
Too big Get file →
Q3_K_M8.7 GB 9.7 GB
Too big Get file →
Q3_K_L9.1 GB 10.0 GB
Too big Get file →
IQ4_XS9.2 GB 10.2 GB
Too big Get file →
IQ4_NL9.5 GB 10.5 GB
Too big Get file →
Q4_09.6 GB 10.5 GB
Too big Get file →
Q4_K_S10.2 GB 11.2 GB
Too big Get file →
Q4_110.6 GB 11.5 GB
Too big Get file →
Q4_K_M11.2 GB 12.1 GB
Too big Get file →
Q5_K_S11.9 GB 12.9 GB
Too big Get file →
Q5_K_M12.7 GB 13.7 GB
Too big Get file →
Q6_K15.1 GB 16.0 GB
Too big Get file →

What GPU do you need for Ling Lite?

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: the best quant that fits is Q2_K_S (7.0 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (10.6 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (15.1 GB file, about 16.0 GB in use).

Which Ling Lite quant should you choose?

Q4_K_M is the usual starting point for Ling Lite: it balances file size and quality well. Here it is a 11.2 GB file.

If memory is tight, the smallest file is IQ1_S at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebailingmoe
Parameters16.8B (approximate, mixture of experts)
Layers28
Trained context16,384 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyLing
Licensemit
Downloads (HF)473
Last updated2025-04-03

Frequently asked questions about Ling Lite

How much VRAM does Ling Lite need?

About 12.1 GB at Q4_K_M with an 8K context window. That is the 11.2 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 Lite on an 8 GB GPU?

Yes, with Q2_K_S: the 7.0 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 Lite GGUF?

It depends on the quant: IQ1_S is 5.4 GB, IQ1_M is 5.6 GB, IQ2_XXS is 6.1 GB, IQ2_XS is 6.4 GB, IQ2_S is 6.5 GB, IQ2_M is 6.8 GB and 18 more.

What context length does Ling Lite support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.9 GB at 16K.

Where can I download Ling Lite GGUF?

The files are on Hugging Face in the mradermacher/Ling-lite-i1-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 Lite 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.

Other GGUFs of Ling-lite

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ling models

All Ling →

Other medium models

All medium models →