Dark Planet 8D Mirrored Chaos needs about 30.6 GB of memory at Q4_K_M (a 29.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 9 quants, from 17.8 GB (Q2_K) to 39.0 GB (Q6_K).
Dark Planet 8D Mirrored Chaos – a 47.5B parameter Llama3 MOE model for vivid creative writing
Dark Planet 8D Mirrored Chaos is a 47.5B parameter Llama3 mixture of experts model. It supports a maximum context of 8192 tokens and excels at roleplay, descriptive prose, and vivid dialogue. The model is licensed under Apache‑2.0 and requires a Llama3 or Command‑R template.
Good at
- Vivid creative writing
- Roleplay with realistic dialogue
- High‑quality descriptive prose
Limits
- No vision support
- Requires Llama3 or Command‑R template
- Large VRAM needed for higher quantizations
Best for
- Writing fiction and roleplay scripts
- Generating detailed descriptive scenes
- Creating varied dialogue for games
Who it’s for. This model is ideal for writers, game designers, and role‑players who need high‑quality, imaginative text. It is suitable for projects that can accommodate its large memory footprint and require detailed, varied prose.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 17.8 GB | 19.3 GB | Too big | Get file → | |
| Q3_K_S | 20.9 GB | 22.5 GB | Too big | Get file → | |
| Q3_K_M | 23.0 GB | 24.6 GB | Too big | Get file → | |
| IQ4_XS | 25.9 GB | 27.5 GB | Too big | Get file → | |
| Q4_K_S | 27.3 GB | 28.9 GB | Too big | Get file → | |
| Q4_K_M | 29.0 GB | 30.6 GB | Too big | Get file → | |
| Q5_K_S | 32.8 GB | 34.4 GB | Too big | Get file → | |
| Q5_K_M | 33.8 GB | 35.4 GB | Too big | Get file → | |
| Q6_K | 39.0 GB | 40.6 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (file size 17.77 GB, estimated 19.3 GB memory). For 12 GB VRAM use Q3_K_S (20.93 GB, 22.5 GB memory). For 16 GB VRAM use Q4_K_S (27.3 GB, 28.9 GB memory). Higher quants provide better quality but need more VRAM.
What GPU do you need for Dark Planet 8D Mirrored Chaos?
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: the best quant that fits is Q3_K_S (20.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (29.0 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (39.0 GB file, about 40.6 GB in use).
Which Dark Planet 8D Mirrored Chaos quant should you choose?
Q4_K_M is the usual starting point for Dark Planet 8D Mirrored Chaos: it balances file size and quality well. Here it is a 29.0 GB file.
If memory is tight, the smallest file is Q2_K at 17.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Dark Planet 8D Mirrored Chaos
How much VRAM does Dark Planet 8D Mirrored Chaos need?
About 30.6 GB at Q4_K_M with an 8K context window. That is the 29.0 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 Dark Planet 8D Mirrored Chaos on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Dark Planet 8D Mirrored Chaos GGUF?
It depends on the quant: Q2_K is 17.8 GB, Q3_K_S is 20.9 GB, Q3_K_M is 23.0 GB, IQ4_XS is 25.9 GB, Q4_K_S is 27.3 GB, Q4_K_M is 29.0 GB and 3 more.
What context length does Dark Planet 8D Mirrored Chaos support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Dark Planet 8D Mirrored Chaos GGUF?
The files are on Hugging Face in the DavidAU/L3-MOE-8X8B-Dark-Planet-8D-Mirrored-Chaos-47B-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 Dark Planet 8D Mirrored Chaos 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 Dark Planet 8D Mirrored Chaos on 8 GB VRAM?
Yes, using the Q2_K quantization which requires approximately 19.3 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What template is required to run this model?
It requires a Llama3 or Command‑R template for proper operation.