MN 12B Celeste V1.9 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 25 quants, from 4.4 GB (IQ2_M) to 49.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
12‑Billion‑parameter story‑writing model with 1M context
MN 12B Celeste V1.9 is a 12 B‑parameter Llama‑based model trained on Mistral NeMo 12B Instruct for story writing and role‑playing. It supports 1 024 000‑token context and is available in multiple GGUF quantizations. The model is released under Apache‑2.0.
Good at
- Story and role‑playing generation
- ChatML‑style dialogue
- Long‑form creative writing
Limits
- Large context requires high VRAM or RAM
- No vision or multimodal support
- Requires GGUF quantization for llama.cpp
Best for
- Creative writers needing long narratives
- Game designers scripting dialogue
- Chatbot developers building role‑play experiences
Who it’s for. Developers and hobbyists who want a large‑context LLM for creative text generation. The model is suitable for local deployment with llama.cpp or LM Studio using the provided GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 6.6 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 7.1 GB | Fits | Get file → | |
| Q2_K_L | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_S | 5.5 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_L | 6.6 GB | 8.4 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_0 | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_0 | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_0 | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_0 | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_S | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_XL | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_L | 8.0 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_L | 9.1 GB | 11.0 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q6_K_L | 10.4 GB | 12.2 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → | |
| F16 | 24.5 GB | 26.3 GB | Too big | Get file → | |
| F32 | 49.0 GB | 50.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (4.44 GB) or Q2_K (4.79 GB). For 12 GB VRAM, Q3_K_L (6.56 GB) or Q4_K_M (7.48 GB) are good choices. For maximum quality on 16 GB VRAM, Q5_K_L (9.14 GB) or Q6_K (10.06 GB) provide higher precision.
What GPU do you need for MN 12B Celeste V1.9?
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).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).
Which MN 12B Celeste V1.9 quant should you choose?
Q4_K_M is the usual starting point for MN 12B Celeste V1.9: 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 IQ2_M at 4.4 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
Source
Frequently asked questions about MN 12B Celeste V1.9
How much VRAM does MN 12B Celeste V1.9 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 Celeste V1.9 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 Celeste V1.9 GGUF?
It depends on the quant: IQ2_M is 4.4 GB, Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q2_K_L is 5.4 GB, Q3_K_S is 5.5 GB, IQ3_M is 5.7 GB and 19 more.
What context length does MN 12B Celeste V1.9 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 Celeste V1.9 GGUF?
The files are on Hugging Face in the bartowski/MN-12B-Celeste-V1.9-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 Celeste V1.9 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 Celeste V1.9 on 8 GB VRAM?
Yes, use a quant such as IQ2_M or Q2_K, which fit within 8 GB of VRAM and use about 6–7 GB of memory at 8K context.
Does the model support vision or multimodal inputs?
No, the model only handles text and does not include vision or multimodal capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.