LI

Ling 3.1 flash 1019 abliterated

LingGGUF by mrfakenameUpdated 2026-10-28
Download on Hugging Face
Parameters4M
Context256K
Layers73
Architecturebailingmoe3
Smallest quant0.0 GB
Quick answer

Ling 3.1 flash 1019 abliterated needs about 400.1 GB of memory at Q4_K_M (a 345.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 0.0 GB to 608.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 215.6 GB.

Ling 3.1 flash 1019 abliterated – a 0.00385B parameter LLM with directional refusal ablation

Ling 3.1 flash 1019 abliterated is a 0.00385B parameter model built on the bailingmoe3 architecture. It is a mixture of experts with 262144 trained context tokens. The model is released under the MIT license and requires llama.cpp with bailingmoe3 support.

Good at

  • Directional refusal ablation
  • Multi‑directional refusal handling
  • Fine‑grained compliance control

Limits

  • No vision support
  • Requires llama.cpp with bailingmoe3
  • Large memory for higher quants

Best for

  • Chat applications needing controlled refusals
  • Research on refusal directionality
  • Fine‑tuning with LoRA

Who it’s for. Developers and researchers who need a lightweight model that retains complex refusal behaviour across multiple directions. The model is suitable for environments where memory is limited but precise control over refusal responses is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 54.4 GB
Too big Get file →
Q3_K_M271.9 GB (15 parts) 326.3 GB
Too big Get file →
Q4_K_M345.7 GB (15 parts) 400.1 GB
Too big Get file →
Q6_K469.8 GB (15 parts) 524.2 GB
Too big Get file →
Q8_0608.3 GB (15 parts) 662.7 GB
Too big Get file →

For 8 GB VRAM, use the Q3_K_M quant (345.71 GB file, 326.3 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (345.71 GB file, 400.1 GB memory) is recommended. Higher quants require more VRAM and are not advised for small GPUs.

What GPU do you need for Ling 3.1 flash 1019 abliterated?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Ling 3.1 flash 1019 abliterated quant should you choose?

Q4_K_M is the usual starting point for Ling 3.1 flash 1019 abliterated: it balances file size and quality well. Here it is a 345.7 GB file.

The Q8_0 file is 608.3 GB, about 1.8 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

Architecturebailingmoe3
Parameters4M (approximate, mixture of experts)
Layers73
Trained context262,144 tokens
KV cache (fp16)6424 KB per token

Source

Quantized bymrfakename
FamilyLing
Licensemit
Downloads (HF)1,327
Last updated2026-10-28

Frequently asked questions about Ling 3.1 flash 1019 abliterated

How much VRAM does Ling 3.1 flash 1019 abliterated need?

About 400.1 GB at Q4_K_M with an 8K context window. That is the 345.7 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 3.1 flash 1019 abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ling 3.1 flash 1019 abliterated GGUF?

It depends on the quant: file is 0.0 GB, Q3_K_M is 271.9 GB, Q4_K_M is 345.7 GB, Q6_K is 469.8 GB, Q8_0 is 608.3 GB.

What context length does Ling 3.1 flash 1019 abliterated support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 53.9 GB at 8K and 215.6 GB at 32K.

Where can I download Ling 3.1 flash 1019 abliterated GGUF?

The files are on Hugging Face in the mrfakename/Ling-3.1-flash-1019-abliterated-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 3.1 flash 1019 abliterated 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 3.1 flash 1019 abliterated on 8 GB VRAM?

Use the Q3_K_M quant; it requires approximately 326.3 GB memory at 8k context, which is beyond 8 GB VRAM, so it is not feasible.

Does this model support vision tasks?

No, the model has no vision capability.

What license does the model use?

The model is released under the MIT license.

Similar models

Browse all →

More from mrfakename

All by mrfakename →

More Ling models

All Ling →

Other tiny models

All tiny models →