Dark Scarlett 27B v2.0 needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 18 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 v2.0 – a 27‑billion‑parameter Qwen‑3.5 model with vision and roleplay abilities
Dark Scarlett 27B v2.0 is a 27‑billion‑parameter model built on the Qwen‑3.5 architecture. It supports vision and roleplay tasks and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for different memory budgets.
Good at
- Vision inference
- Roleplay dialogue
- Large context handling
Limits
- Requires 8‑k context for estimates
- No mixture of experts
- License is Apache‑2.0
Best for
- Chatbots needing image understanding
- Creative writing with roleplay
- Long‑form content generation
Who it’s for. Developers building applications that need both text and image understanding in a single model. The model is suitable for research and production use where an open‑source license is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| — | 3.2 GB | 5.8 GB | Fits | Get file → | |
| BF16 | 5.9 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q4_0 | 15.7 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_M | 17.0 GB | 19.7 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_S | 19.2 GB | 21.8 GB | Too big | Get file → | |
| IQ4_NL | 19.4 GB | 22.1 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q4_K_M | 20.1 GB | 22.8 GB | Too big | Get file → | |
| Q5_K_S | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q5_K_M | 22.7 GB | 25.4 GB | Too big | Get file → | |
| Q6_K | 25.4 GB | 28.1 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → | |
| Q8_0 | 31.4 GB | 34.1 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_0 (15.72 GB file, ~18.4 GB memory at 8k context). For 12‑GB VRAM, Q5_K_M (19.54 GB file, ~22.2 GB memory). For 16‑GB VRAM, Q6_K (22.43 GB file, ~25.1 GB memory). Estimates are approximate.
What GPU do you need for Dark Scarlett 27B v2.0?
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 (3.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (3.2 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 8.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (20.1 GB file, about 22.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 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 v2.0 quant should you choose?
Q4_K_M is the usual starting point for Dark Scarlett 27B v2.0: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.0 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 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 v2.0
How much VRAM does Dark Scarlett 27B v2.0 need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 v2.0 on an 8 GB GPU?
Yes, with the smaller files: the 3.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dark Scarlett 27B v2.0 GGUF?
It depends on the quant: file is 0.0 GB, file is 3.2 GB, BF16 is 5.9 GB, Q3_K_M is 13.5 GB, Q4_0 is 15.7 GB, Q4_K_M is 16.8 GB and 12 more.
What context length does Dark Scarlett 27B v2.0 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 v2.0 GGUF?
The files are on Hugging Face in the ReadyArt/Dark-Scarlett-27B-v2.0-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 v2.0 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 v2.0 on 8 GB VRAM?
Use the Q4_0 quantization; it requires about 18.4 GB of VRAM at 8k context, so 8 GB is insufficient.
Does the model support vision tasks?
Yes, the model has vision capabilities as indicated in its detected abilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.