MN 12B Faun RP RU needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.1 GB (Q3_K_M) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
MN 12B Faun RP RU – a 12.2B‑parameter Russian roleplay model
MN 12B Faun RP RU is a TIES‑merged model based on Mistral Nemo 12B. It focuses on stable roleplay, improved Russian fluency, and a rich vocabulary. The model supports long contexts up to ~8192 tokens and follows instructions while occasionally adding safety disclaimers.
Good at
- Stable roleplay in Russian
- Long‑context handling up to ~8192 tokens
- Rich vocabulary including expressive and NSFW terms
Limits
- No vision support
- May add safety disclaimers on sensitive prompts
- No post‑merge fine‑tuning
Best for
- Russian roleplay characters
- Long‑form dialogue generation
- Creative writing in Russian
Who it’s for. Developers and content creators needing a Russian‑centric LLM for roleplay or dialogue tasks. The model is suitable for applications that can tolerate occasional safety notices and do not require vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 7.48 GB, estimated 9.3 GB memory). For 12 GB VRAM, Q5_K_M (8.73 GB, 10.6 GB). For 16 GB VRAM, Q6_K (10.06 GB, 11.9 GB). Higher‑quality quants need more VRAM.
What GPU do you need for MN 12B Faun RP RU?
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 Q3_K_M (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
Which MN 12B Faun RP RU quant should you choose?
Q4_K_M is the usual starting point for MN 12B Faun RP RU: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.0 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.
If memory is tight, the smallest file is Q3_K_M at 6.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MN 12B Faun RP RU
How much VRAM does MN 12B Faun RP RU need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 12B Faun RP RU on an 8 GB GPU?
Yes, with Q3_K_M: 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 MN 12B Faun RP RU GGUF?
It depends on the quant: Q3_K_M is 6.1 GB, Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB, Q8_0 is 13.0 GB.
What context length does MN 12B Faun RP RU 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download MN 12B Faun RP RU GGUF?
The files are on Hugging Face in the limloop/MN-12B-Faun-RP-RU-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 MN 12B Faun RP RU 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 MN 12B Faun RP RU on 8 GB VRAM?
Yes, with the Q4_K_M quant the estimated memory is 9.3 GB at 8k context, which fits an 8 GB VRAM setup with some overhead.
Does the model support vision tasks?
No, the model has no vision capability.
Will the model block sensitive content?
It may add safety disclaimers but does not block generation; output continues after the disclaimer.