CE

MN 12B Celeste V1.9

CelesteGGUF by mradermacherUpdated 2024-08-01
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

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 14 quants, from 4.8 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

MN 12B Celeste V1.9 – 12.2B parameter story writing model

MN 12B Celeste V1.9 is a 12.2B parameter Llama‑based model trained on Mistral NeMo 12B Instruct with 8K context. It is optimized for story writing and roleplaying, using ChatML tokens to avoid EOS bleeding. The model is released under the apache-2.0 license.

Good at

  • Story writing
  • Roleplaying
  • ChatML compatible

Limits

  • No vision support
  • Large context requires high VRAM
  • No explicit language support listed

Best for

  • Creative fiction generation
  • Interactive roleplay sessions
  • ChatML based applications

Who it’s for. Developers and writers who need a large language model for narrative tasks. The model is suitable for local deployment with sufficient GPU memory and for integration into chat interfaces that support ChatML.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_S5.6 GB 7.4 GB
Tight Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.8 GB 8.6 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.79 GB file, 6.6 GB memory at 8K). For 12 GB VRAM, Q4_K_M (7.48 GB file, 9.3 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (8.73 GB file, 10.6 GB memory) offers higher quality.

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).

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 Q2_K at 4.8 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

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyCeleste
Licenseapache-2.0
Downloads (HF)661
Last updated2024-08-01

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: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.5 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.1 GB and 8 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 mradermacher/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, the Q2_K quant requires 6.6 GB memory at 8K context, which fits within 8 GB VRAM.

Does the model support vision or image inputs?

No, the model has no vision support and is text‑only.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of MN-12B-Celeste-V1.9

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Celeste models

All Celeste →

Other medium models

All medium models →