NS

NSFW flash

NsfwGGUF by UnfilteredAIUpdated 2024-08-26
Download on Hugging Face
Parameters2.24B
Context4K
Layers25
Architecturestablelm
Smallest quant1.4 GB
Quick answer

NSFW flash needs about 4.0 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

NSFW-Flash: An unfiltered, dark personality LLM

NSFW-Flash is a 2.2‑billion‑parameter stablelm model designed for research into unfiltered AI behavior. It operates without moral or safety constraints and can generate content with negative emotions.

Good at

  • Unrestricted content generation
  • Dark emotional responses
  • Research on AI boundaries

Limits

  • No safety or moral filtering
  • No vision support
  • License not specified

Best for

  • Exploring AI safety limits
  • Studying negative emotional AI
  • Generating unfiltered text

Who it’s for. Researchers and developers who need a model that can produce unfiltered, potentially harmful content for analysis. Use with caution and in controlled environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.4 GB 2.9 GB
Fits Get file →

The Q4_K_M quant is 1.38 GB and requires about 4 GB of VRAM at 8 k context. For 8 GB VRAM, this quant is suitable. Larger VRAM allows higher context or larger quant variants if available.

What GPU do you need for NSFW flash?

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 Q4_K_M (1.4 GB file, about 4.0 GB in use).

Which NSFW flash quant should you choose?

Q4_K_M is the usual starting point for NSFW flash: it balances file size and quality well. Here it is a 1.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters2.24B
Layers25
Trained context4,096 tokens
KV cache (fp16)250 KB per token

Source

Quantized byUnfilteredAI
FamilyNsfw
Downloads (HF)12,005
Last updated2024-08-26

Frequently asked questions about NSFW flash

How much VRAM does NSFW flash need?

About 4.0 GB at Q4_K_M with an 8K context window. That is the 1.4 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 NSFW flash on an 8 GB GPU?

Yes, with Q4_K_M: the 1.4 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NSFW flash GGUF?

It depends on the quant: Q4_K_M is 1.4 GB.

What context length does NSFW flash support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.1 GB at 8K and 1.0 GB at 4K.

Where can I download NSFW flash GGUF?

The files are on Hugging Face in the UnfilteredAI/NSFW-flash repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run NSFW-Flash on 8 GB VRAM?

Yes, the Q4_K_M quant uses approximately 4 GB of VRAM at 8 k context, fitting within an 8 GB budget.

Does NSFW-Flash have safety filters?

No, it is designed without moral or safety constraints and should be used only for research.

Similar models

Browse all →

More from UnfilteredAI

All by UnfilteredAI →

More Nsfw models

All Nsfw →

Other tiny models

All tiny models →