Ministral-3-14B-Nymphaea-RP needs about 10.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 11.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral‑3‑14B‑Nymphaea‑RP – a fine‑tuned roleplay model
Ministral‑3‑14B‑Nymphaea‑RP is a 13.5 billion‑parameter model fine‑tuned for roleplay and creative writing. It is based on the Mistral‑3 architecture and trained with DoRA LoRA on a 400k‑token dataset. The model is released under the apache‑2.0 license.
Good at
- Roleplay dialogue
- Creative story generation
- Instruct‑style prompts
Limits
- Large context requires high VRAM
- No vision support in this GGUF release
- Requires 8 k context for memory estimates
Best for
- Chatbot roleplay scenarios
- Writing fiction drafts
- Interactive storytelling
Who it’s for. Developers and hobbyists who need a roleplay‑focused LLM with a 13.5 billion‑parameter base. The model is suitable for local deployment using llama.cpp and supports mixed‑quant GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 3.3 GB | 5.1 GB | Fits | Get file → | |
| IQ1_M | 3.5 GB | 5.3 GB | Fits | Get file → | |
| IQ2_XXS | 3.9 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XS | 4.3 GB | 6.1 GB | Fits | Get file → | |
| IQ2_S | 4.5 GB | 6.4 GB | Fits | Get file → | |
| IQ2_M | 4.8 GB | 6.7 GB | Fits | Get file → | |
| Q2_K_S | 4.9 GB | 6.8 GB | Fits | Get file → | |
| Q2_K | 5.2 GB | 7.1 GB | Fits | Get file → | |
| IQ3_XXS | 5.4 GB | 7.3 GB | Tight | Get file → | |
| IQ3_XS | 5.8 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 6.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_S | 6.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_M | 6.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 6.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_L | 7.2 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 7.4 GB | 9.3 GB | Too big | Get file → | |
| IQ4_NL | 7.8 GB | 9.6 GB | Too big | Get file → | |
| Q4_0 | 7.8 GB | 9.6 GB | Too big | Get file → | |
| Q4_K_S | 7.8 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_M | 8.2 GB | 10.1 GB | Too big | Get file → | |
| Q4_1 | 8.6 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_S | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_M | 9.6 GB | 11.5 GB | Too big | Get file → | |
| Q6_K | 11.1 GB | 12.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 8.24 GB, ~10.1 GB memory at 8 k context). With 16 GB VRAM Q4_K_L (7.21 GB, ~9.1 GB memory) fits comfortably. For higher quality, Q5_K_M (9.62 GB, ~11.5 GB memory) is recommended if you have 12 GB VRAM.
What GPU do you need for Ministral-3-14B-Nymphaea-RP?
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 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XXS (3.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.6 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.1 GB file, about 12.9 GB in use).
Which Ministral-3-14B-Nymphaea-RP quant should you choose?
Q4_K_M is the usual starting point for Ministral-3-14B-Nymphaea-RP: it balances file size and quality well. Here it is a 8.2 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
Source
Frequently asked questions about Ministral-3-14B-Nymphaea-RP
How much VRAM does Ministral-3-14B-Nymphaea-RP need?
About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.2 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 Ministral-3-14B-Nymphaea-RP on an 8 GB GPU?
Yes, with IQ3_S: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral-3-14B-Nymphaea-RP GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.3 GB, IQ2_S is 4.5 GB and 19 more.
What context length does Ministral-3-14B-Nymphaea-RP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Ministral-3-14B-Nymphaea-RP GGUF?
The files are on Hugging Face in the mradermacher/Ministral-3-14B-Nymphaea-RP-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 Ministral-3-14B-Nymphaea-RP 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, using the Q4_K_M quantization which requires about 10.1 GB memory at 8 k context.
Does this model support vision?
The base weights retain native vision capabilities, but the GGUF release does not include mmproj files.
What license applies to this model?
The model is released under the apache‑2.0 license.