Dark Scarlett 27B v3.0 needs about 26.2 GB of memory at Q4_K_M (a 23.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 0.0 GB to 31.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Dark Scarlett 27B v3.0 – a 27.3B parameter Qwen‑35 model
Dark Scarlett 27B v3.0 is a 27.3B parameter model built on the Qwen‑35 architecture. It supports a 262144 token context window and is released under the Apache‑2.0 license. The model is optimized for role‑play tasks.
Good at
- Large context handling
- Role‑play scenarios
- High‑capacity language modeling
Limits
- No vision support
- Large VRAM requirement for full precision
- Requires Apache‑2.0 compatible usage
Best for
- Chatbots needing long context
- Creative writing with extended prompts
- Role‑play simulations
Who it’s for. Developers and researchers building conversational agents that require extensive context and role‑play capabilities. The model is suitable for applications where a large token window is critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XS | 20.0 GB | 22.7 GB | Too big | Get file → | |
| Q3_K_M | 21.2 GB | 23.9 GB | Too big | Get file → | |
| IQ4_XS | 22.2 GB | 24.9 GB | Too big | Get file → | |
| IQ4_NL | 22.7 GB | 25.4 GB | Too big | Get file → | |
| Q4_K_S | 22.8 GB | 25.5 GB | Too big | Get file → | |
| Q4_K_M | 23.5 GB | 26.2 GB | Too big | Get file → | |
| Q5_K_S | 24.9 GB | 27.6 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 28.0 GB | Too big | Get file → | |
| Q6_K | 27.2 GB | 29.9 GB | Too big | Get file → | |
| Q8_0 | 31.4 GB | 34.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (23.47 GB file, 26.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (25.28 GB file, 28 GB memory) is a good balance. For 16 GB VRAM, Q6_K (27.21 GB file, 29.9 GB memory) provides higher quality.
What GPU do you need for Dark Scarlett 27B v3.0?
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: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_M (21.2 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.2 GB file, about 29.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (31.4 GB file, about 34.1 GB in use).
Which Dark Scarlett 27B v3.0 quant should you choose?
Q4_K_M is the usual starting point for Dark Scarlett 27B v3.0: it balances file size and quality well. Here it is a 23.5 GB file.
The Q8_0 file is 31.4 GB, about 1.3 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Dark Scarlett 27B v3.0
How much VRAM does Dark Scarlett 27B v3.0 need?
About 26.2 GB at Q4_K_M with an 8K context window. That is the 23.5 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 Dark Scarlett 27B v3.0 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dark Scarlett 27B v3.0 GGUF?
It depends on the quant: file is 0.0 GB, IQ3_XS is 20.0 GB, Q3_K_M is 21.2 GB, IQ4_XS is 22.2 GB, IQ4_NL is 22.7 GB, Q4_K_S is 22.8 GB and 5 more.
What context length does Dark Scarlett 27B v3.0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Dark Scarlett 27B v3.0 GGUF?
The files are on Hugging Face in the ReadyArt/Dark-Scarlett-27B-v3.0-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 Dark Scarlett 27B v3.0 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 Dark Scarlett 27B v3.0 on 8 GB VRAM?
Use the Q4_K_M quantized file; it requires about 26.2 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.
Does this model support image inputs?
No, the model has no vision capabilities.