LI

Ling 3.0 Tiny Uncensored Abliterated

LingGGUF by mradermacherUpdated 2026-08-21
Download on Hugging Face
Parameters7.89B
Context128K
Layers24
Architecturebailingmoe3
Smallest quant0.0 GB
Quick answer

Ling 3.0 Tiny Uncensored Abliterated needs about 9.8 GB of memory at Q4_K_M (a 4.8 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 6.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.

Ling 3.0 Tiny Uncensored Abliterated – a 7.89B MoE model for cybersecurity and red‑team tasks

Ling 3.0 Tiny Uncensored Abliterated is a 7.89B parameter model built on the bailingmoe3 architecture. It is a weights‑level uncensored derivative that removes refusal directions and runs on Apple Silicon via a triton‑free pure‑torch implementation. The model supports a 131072 token context window.

Good at

  • Cybersecurity and red‑team content
  • Uncensored, direct answers
  • Apple Silicon compatibility

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is MIT – no commercial restrictions

Best for

  • Security researchers needing uncensored answers
  • Red‑team simulations on macOS
  • Low‑latency inference on Apple GPUs

Who it’s for. Security professionals and researchers who need uncensored, direct responses on cybersecurity topics and who run inference on Apple Silicon. The model is suitable for environments where CUDA or Triton are unavailable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 5.0 GB
Fits Get file →
IQ1_S1.8 GB 6.7 GB
Fits Get file →
IQ1_M1.9 GB 6.9 GB
Fits Get file →
IQ2_XXS2.2 GB 7.1 GB
Fits Get file →
IQ2_XS2.4 GB 7.4 GB
Tight Get file →
IQ2_S2.5 GB 7.4 GB
Tight Get file →
IQ2_M2.7 GB 7.6 GB
Tight Get file →
Q2_K_S2.8 GB 7.7 GB
Tight Get file →
Q2_K3.0 GB 7.9 GB
Tight Get file →
IQ3_XXS3.1 GB 8.1 GB
Too big Get file →
IQ3_XS3.3 GB 8.3 GB
Too big Get file →
IQ3_S3.5 GB 8.4 GB
Too big Get file →
Q3_K_S3.5 GB 8.4 GB
Too big Get file →
IQ3_M3.6 GB 8.5 GB
Too big Get file →
Q3_K_M3.8 GB 8.8 GB
Too big Get file →
Q3_K_L4.1 GB 9.1 GB
Too big Get file →
IQ4_XS4.3 GB 9.2 GB
Too big Get file →
IQ4_NL4.5 GB 9.5 GB
Too big Get file →
Q4_04.5 GB 9.5 GB
Too big Get file →
Q4_K_S4.6 GB 9.5 GB
Too big Get file →
Q4_K_M4.8 GB 9.8 GB
Too big Get file →
Q4_15.0 GB 9.9 GB
Too big Get file →
Q5_K_S5.5 GB 10.4 GB
Too big Get file →
Q5_K_M5.6 GB 10.6 GB
Too big Get file →
Q6_K6.5 GB 11.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.76 GB) or IQ1_M (1.93 GB). If 12 GB is available, Q3_K_M (3.84 GB) or Q4_K_M (4.82 GB) provide a good balance of size and performance. Larger quants such as Q5_K_M (5.64 GB) or Q6_K (6.5 GB) require more memory but offer higher fidelity.

What GPU do you need for Ling 3.0 Tiny Uncensored 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: 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 (6.5 GB file, about 11.4 GB in use).

Which Ling 3.0 Tiny Uncensored Abliterated quant should you choose?

Q4_K_M is the usual starting point for Ling 3.0 Tiny Uncensored Abliterated: it balances file size and quality well. Here it is a 4.8 GB file.

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
Parameters7.89B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)528 KB per token

Source

Quantized bymradermacher
FamilyLing
Licensemit
Downloads (HF)1,795
Last updated2026-08-21

Frequently asked questions about Ling 3.0 Tiny Uncensored Abliterated

How much VRAM does Ling 3.0 Tiny Uncensored Abliterated need?

About 9.8 GB at Q4_K_M with an 8K context window. That is the 4.8 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 Uncensored Abliterated 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 Uncensored Abliterated GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.8 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.4 GB, IQ2_S is 2.5 GB and 19 more.

What context length does Ling 3.0 Tiny Uncensored Abliterated 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 Uncensored Abliterated GGUF?

The files are on Hugging Face in the mradermacher/Ling-3.0-tiny-Uncensored-Abliterated-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 3.0 Tiny Uncensored 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.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model was trained with a 131072 token context window.

Other GGUFs of Ling-3.0-tiny-Uncensored-Abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ling models

All Ling →

Other small models

All small models →