ST

StarDust 12b v2

StardustGGUF by bartowskiUpdated 2024-09-03
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.4 GB
Quick answer

StarDust 12b v2 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 24 quants, from 4.4 GB (IQ2_M) to 24.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

StarDust 12b v2 – a role‑play focused Llama model

StarDust 12b v2 is a 12.2 billion parameter Llama model optimized for role‑playing. It was merged using the DARE TIES method and is available in multiple GGUF quantizations. The model is licensed under apache‑2.0 and is not recommended for general conversational use.

Good at

  • Creative role‑play
  • Long narrative generation
  • Impersonation tasks

Limits

  • Not suitable for general conversation
  • No vision support
  • Requires large VRAM for higher quants

Best for

  • Story writers
  • Game designers
  • Chatbot agents

Who it’s for. Developers and writers who need a dedicated role‑play model. The model performs best when used with ChatML prompts and is not intended for general instruction or conversational tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q2_K_L5.4 GB 7.3 GB
Tight Get file →
Q3_K_S5.5 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_XS6.7 GB 8.6 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q3_K_XL7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q4_K_L8.0 GB 9.8 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 →
Q5_K_L9.1 GB 11.0 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q6_K_L10.4 GB 12.2 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →
F1624.5 GB 26.3 GB
Too big Get file →

For 8 GB VRAM, the Q4_K_M quant (file size 7.48 GB, estimated memory 9.3 GB) is a good balance. If you have 12 GB VRAM, consider Q5_K_M (8.73 GB, 10.6 GB). For 16 GB VRAM, Q6_K (10.06 GB, 11.9 GB) or Q8_0 (13.02 GB, 14.9 GB) provide higher quality.

What GPU do you need for StarDust 12b v2?

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).

Which StarDust 12b v2 quant should you choose?

Q4_K_M is the usual starting point for StarDust 12b v2: 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

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

Source

Quantized bybartowski
FamilyStardust
Licenseapache-2.0
Downloads (HF)631
Last updated2024-09-03

Frequently asked questions about StarDust 12b v2

How much VRAM does StarDust 12b v2 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 StarDust 12b v2 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 StarDust 12b v2 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 18 more.

What context length does StarDust 12b v2 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 StarDust 12b v2 GGUF?

The files are on Hugging Face in the bartowski/StarDust-12b-v2-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 StarDust 12b v2 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 StarDust 12b v2 on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 9.3 GB of VRAM at 8k context, which is close to 8 GB but may need swapping. For a smoother experience, use a lower quant like Q2_K.

Does StarDust 12b v2 support vision?

No, the model does not have vision capabilities.

Other GGUFs of StarDust-12b-v2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Stardust models

All Stardust →

Other medium models

All medium models →