LI

Ling-3.0-tiny-base-midtrain

LingGGUF by FriskyFennecUpdated 2026-09-11
Download on Hugging Face
Parameters8.21B
Context256K
Layers25
Architecturebailingmoe3
Smallest quant3.6 GB
Quick answer

Ling-3.0-tiny-base-midtrain 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 13 quants, from 3.6 GB (Q3_K_S) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 18.5 GB.

Ling-3.0-tiny-base-midtrain is a 8.21B-parameter Ling model in GGUF format, quantized by FriskyFennec. Its trained context length is 256K tokens. The repository has 13 quant files, from 3.6 GB (Q3_K_S) to 16.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.6 GB 8.8 GB
Too big Get file →
Q3_K4.0 GB 9.1 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 →

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

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-midtrain quant should you choose?

Q4_K_M is the usual starting point for Ling-3.0-tiny-base-midtrain: 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
Parameters8.21B (approximate, mixture of experts)
Layers25
Trained context262,144 tokens
KV cache (fp16)550 KB per token

Source

Quantized byFriskyFennec
FamilyLing
Licensemit
Downloads (HF)198
Last updated2026-09-11

Frequently asked questions about Ling-3.0-tiny-base-midtrain

How much VRAM does Ling-3.0-tiny-base-midtrain 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-midtrain 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-midtrain GGUF?

It depends on the quant: Q3_K_S is 3.6 GB, Q3_K is 4.0 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 and 7 more.

What context length does Ling-3.0-tiny-base-midtrain support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 4.6 GB at 8K and 18.5 GB at 32K.

Where can I download Ling-3.0-tiny-base-midtrain GGUF?

The files are on Hugging Face in the FriskyFennec/Ling-3.0-tiny-base-midtrain-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-midtrain 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-3.0-tiny-base-midtrain

Similar models

Browse all →

More from FriskyFennec

All by FriskyFennec →

More Ling models

All Ling →

Other small models

All small models →