self after dark needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.9 GB (Q4_K_M) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Uncensored Llama‑3.1‑8B base model for realistic, emotional chat
Self: After Dark is an 8.03 B parameter Llama‑3.1‑8B base model. It was trained without censorship and focuses on realistic, emotionally resonant conversations. The model is free under the Apache‑2.0 license.
Good at
- Realistic, emotional dialogue
- Uncensored content generation
- Short, natural‑sounding messages
Limits
- No vision support
- No built‑in helpful‑assistant behavior
- Requires 8 k context for memory estimates
Best for
- Chatting with a virtual persona
- Role‑playing scenarios
- Creative writing prompts
Who it’s for. Developers and hobbyists who need an uncensored, conversational LLM for chat or creative projects. The model is ideal for applications that can handle or filter NSFW content.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant (4.92 GB file, ~6.5 GB memory at 8 k context). For 12 GB VRAM use Q8_0 (8.54 GB file, ~10.1 GB memory at 8 k context). Memory estimates are approximate.
What GPU do you need for self after dark?
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: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
Which self after dark quant should you choose?
Q4_K_M is the usual starting point for self after dark: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about self after dark
How much VRAM does self after dark need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 self after dark on an 8 GB GPU?
Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of self after dark GGUF?
It depends on the quant: Q4_K_M is 4.9 GB, Q8_0 is 8.5 GB.
What context length does self after dark support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download self after dark GGUF?
The files are on Hugging Face in the Gurubot/self-after-dark repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does self after dark 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 Self: After Dark on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 6.5 GB of VRAM at 8 k context, fitting within an 8 GB budget.
Does the model support image input?
No, Self: After Dark is a text‑only model with no vision capabilities.
Is the model suitable for production use?
It is free under Apache‑2.0, but its uncensored nature may require content moderation for production deployments.