MN DARKEST UNIVERSE 29B needs about 21.5 GB of memory at Q4_K_M (a 17.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 6.6 GB (IQ1_S) to 23.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.7 GB.
29B‑parameter Llama model focused on roleplay
MN DARKEST UNIVERSE 29B is a 29.2‑billion‑parameter Llama architecture model. It is optimized for roleplay scenarios and available in multiple GGUF quantizations. The model was trained on a context of 1,024,000 tokens.
Good at
- Roleplay dialogue
- Creative storytelling
- Character interaction
Limits
- No vision support
- License not specified
- Large VRAM requirement for higher quants
Best for
- Chatbot roleplay engines
- Narrative generation
- Interactive fiction
Who it’s for. Developers building roleplay‑centric chatbots or interactive fiction systems that require deep contextual understanding. The model is suitable for users with access to sufficient GPU memory to run higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.6 GB | 10.5 GB | Too big | Get file → | |
| IQ1_M | 7.1 GB | 11.1 GB | Too big | Get file → | |
| IQ2_XXS | 8.1 GB | 12.0 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 12.8 GB | Too big | Get file → | |
| IQ2_S | 9.4 GB | 13.3 GB | Too big | Get file → | |
| IQ2_M | 10.1 GB | 14.1 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 14.9 GB | Too big | Get file → | |
| IQ3_XXS | 11.4 GB | 15.4 GB | Too big | Get file → | |
| IQ3_XS | 12.2 GB | 16.1 GB | Too big | Get file → | |
| Q3_K_S | 12.8 GB | 16.7 GB | Too big | Get file → | |
| IQ3_S | 12.9 GB | 16.8 GB | Too big | Get file → | |
| IQ3_M | 13.3 GB | 17.2 GB | Too big | Get file → | |
| Q3_K_M | 14.2 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_L | 15.4 GB | 19.3 GB | Too big | Get file → | |
| IQ4_XS | 15.8 GB | 19.7 GB | Too big | Get file → | |
| Q4_0 | 16.6 GB | 20.6 GB | Too big | Get file → | |
| Q4_K_S | 16.7 GB | 20.6 GB | Too big | Get file → | |
| Q4_K_M | 17.6 GB | 21.5 GB | Too big | Get file → | |
| Q5_K_S | 20.1 GB | 24.1 GB | Too big | Get file → | |
| Q5_K_M | 20.7 GB | 24.6 GB | Too big | Get file → | |
| Q6_K | 23.9 GB | 27.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.57 GB file, 10.5 GB memory). For 12 GB VRAM, IQ2_XS (8.91 GB file, 12.8 GB memory). For 16 GB VRAM, Q4_K_M (17.6 GB file, 21.5 GB memory). Memory estimates are approximate.
What GPU do you need for MN DARKEST UNIVERSE 29B?
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: the best quant that fits is IQ2_XXS (8.1 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (11.4 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (17.6 GB file, about 21.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.9 GB file, about 27.8 GB in use).
Which MN DARKEST UNIVERSE 29B quant should you choose?
Q4_K_M is the usual starting point for MN DARKEST UNIVERSE 29B: it balances file size and quality well. Here it is a 17.6 GB file.
If memory is tight, the smallest file is IQ1_S at 6.6 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 MN DARKEST UNIVERSE 29B
How much VRAM does MN DARKEST UNIVERSE 29B need?
About 21.5 GB at Q4_K_M with an 8K context window. That is the 17.6 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 MN DARKEST UNIVERSE 29B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MN DARKEST UNIVERSE 29B GGUF?
It depends on the quant: IQ1_S is 6.6 GB, IQ1_M is 7.1 GB, IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB, IQ2_M is 10.1 GB and 15 more.
What context length does MN DARKEST UNIVERSE 29B support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.7 GB at 32K.
Where can I download MN DARKEST UNIVERSE 29B GGUF?
The files are on Hugging Face in the mradermacher/MN-DARKEST-UNIVERSE-29B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, using the IQ1_S quantization which requires about 10.5 GB of VRAM at 8k context.
Does this model support vision?
No, the model has no vision capabilities.
What is the context length?
The model was trained on 1,024,000 tokens of context.