Violet Twilight v0.2 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 20 quants, from 3.0 GB (IQ1_S) to 49.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
12B LLaMA model focused on roleplay, available in multiple GGUF quantizations
Violet Twilight v0.2 is a 12‑billion‑parameter LLaMA model trained on ChatML. It is a SLERP merge of Azure_Dusk‑v0.2 and Crimson_Dawn‑v0.2. The model is released under Apache‑2.0 and supports roleplay tasks.
Good at
- ChatML‑style roleplay
- SLERP‑merged content
- Apache‑2.0 licensed
Limits
- No vision support
- Large context requires high VRAM
- No explicit language support list
Best for
- Interactive storytelling
- Character dialogue generation
- Role‑playing game scripts
Who it’s for. Developers and hobbyists who need a roleplay‑oriented LLaMA model with open licensing. The model is suitable for local inference with GGUF support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.0 GB | 4.8 GB | Fits | Get file → | |
| IQ2_XXS | 3.6 GB | 5.4 GB | Fits | Get file → | |
| IQ2_XS | 3.9 GB | 5.8 GB | Fits | Get file → | |
| IQ3_XXS | 4.9 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_S | 5.5 GB | 7.4 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 → | |
| IQ4_NL | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_S | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 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_1 | 9.2 GB | 11.1 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 → | |
| BF16 | 24.5 GB | 26.3 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 IQ1_S (3 GB file, ~4.8 GB VRAM). With 12 GB VRAM, Q4_K_M (7.48 GB file, ~9.3 GB VRAM) or Q5_K_S (8.52 GB file, ~10.4 GB VRAM) provide a good balance of size and performance. Larger VRAM allows Q6_K or Q8_0 for higher quality.
What GPU do you need for Violet Twilight v0.2?
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: the best quant that fits is IQ2_XS (3.9 GB file, about 5.8 GB in use).
- 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 BF16 (24.5 GB file, about 26.3 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).
Which Violet Twilight v0.2 quant should you choose?
Q4_K_M is the usual starting point for Violet Twilight v0.2: 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 IQ1_S at 3.0 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 Violet Twilight v0.2
How much VRAM does Violet Twilight v0.2 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 Violet Twilight v0.2 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 Violet Twilight v0.2 GGUF?
It depends on the quant: IQ1_S is 3.0 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ3_XXS is 4.9 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.5 GB and 14 more.
What context length does Violet Twilight v0.2 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 Violet Twilight v0.2 GGUF?
The files are on Hugging Face in the Epiculous/Violet_Twilight-v0.2-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 Violet Twilight v0.2 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 Violet Twilight v0.2 on 8 GB VRAM?
Yes, the IQ1_S quantization requires about 4.8 GB VRAM at 8k context, fitting within 8 GB.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.