RO

L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B

RogueGGUF by mradermacherUpdated 2025-12-05
Download on Hugging Face
Parameters7.14B
Context128K
Layers67
Architecturellama
Smallest quant0.0 GB
Quick answer

L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B needs about 7.1 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.0 GB.

L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B – a horror‑focused Llama 3.2 model

This 7.14B parameter Llama 3.2 model is fine‑tuned on a horror dataset and expands the base model to 67 layers. It supports a maximum context of 131072 tokens and is designed for detailed prose and role‑play. The model is released under the apache‑2.0 license.

Good at

  • Detailed horror prose
  • Role‑play scenarios
  • Instruction following with high temperature

Limits

  • No vision support
  • Requires Llama3 or Command‑R template
  • Large VRAM needed for higher quant levels

Best for

  • Writing horror fiction
  • Interactive role‑play sessions
  • Generating detailed scene descriptions

Who it’s for. Developers and writers who need a specialized horror narrative model. It is suitable for applications that require deep context and detailed storytelling, such as game scripts or immersive storytelling tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.8 GB
Fits Get file →
IQ1_S1.7 GB 4.4 GB
Fits Get file →
IQ1_M1.8 GB 4.6 GB
Fits Get file →
IQ2_XXS2.0 GB 4.8 GB
Fits Get file →
IQ2_XS2.2 GB 5.0 GB
Fits Get file →
IQ2_S2.4 GB 5.1 GB
Fits Get file →
IQ2_M2.6 GB 5.3 GB
Fits Get file →
Q2_K_S2.6 GB 5.3 GB
Fits Get file →
Q2_K2.8 GB 5.6 GB
Fits Get file →
IQ3_XXS2.8 GB 5.6 GB
Fits Get file →
IQ3_XS3.1 GB 5.8 GB
Fits Get file →
IQ3_S3.2 GB 6.0 GB
Fits Get file →
Q3_K_S3.2 GB 6.0 GB
Fits Get file →
IQ3_M3.4 GB 6.1 GB
Fits Get file →
Q3_K_M3.6 GB 6.3 GB
Fits Get file →
Q3_K_L3.9 GB 6.6 GB
Fits Get file →
IQ4_XS3.9 GB 6.7 GB
Fits Get file →
IQ4_NL4.1 GB 6.9 GB
Fits Get file →
Q4_04.1 GB 6.9 GB
Fits Get file →
Q4_K_S4.2 GB 6.9 GB
Fits Get file →
Q4_K_M4.4 GB 7.1 GB
Fits Get file →
Q4_14.5 GB 7.3 GB
Tight Get file →
Q5_K_S5.0 GB 7.7 GB
Tight Get file →
Q5_K_M5.1 GB 7.8 GB
Tight Get file →
Q6_K5.9 GB 8.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.4 GB memory at 8 k context) or IQ1_M (4.6 GB). With 12 GB VRAM, IQ2_S (5 GB) or Q2_K (5.6 GB) are suitable. For 16 GB VRAM, consider IQ3_S (6 GB) or Q3_K_M (6.3 GB). Memory estimates are approximate.

What GPU do you need for L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B?

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: the best quant that fits is the main file (0.0 GB file, about 2.8 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_S (3.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 8.6 GB in use).

Which L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B quant should you choose?

Q4_K_M is the usual starting point for L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B: it balances file size and quality well. Here it is a 4.4 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

Architecturellama
Parameters7.14B
Layers67
Trained context131,072 tokens
KV cache (fp16)268 KB per token

Frequently asked questions about L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B

How much VRAM does L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B need?

About 7.1 GB at Q4_K_M with an 8K context window. That is the 4.4 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 L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB and 19 more.

What context length does L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.2 GB at 8K and 9.0 GB at 32K.

Where can I download L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B GGUF?

The files are on Hugging Face in the mradermacher/L3.2-Rogue-Creative-Instruct-DARK-HORROR-Uncensored-Abliterated-7B-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 L3.2 Rogue Creative Instruct DARK HORROR Uncensored Abliterated 7B use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which require about 4.4–4.6 GB of VRAM at 8 k context.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of L3.2-Rogue-Creative-Instruct-DARK-HORROR-Uncensored-Abliterated-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rogue models

All Rogue →

Other small models

All small models →