Darkstar Harness needs about 19.1 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 4.4 GB (Q8_0) to 22.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Darkstar Harness – a 4.17B Qwen‑35 model with reasoning, tools, and vision
Darkstar Harness is a 4.17B parameter Qwen‑35 architecture model. It supports reasoning, tool use, and vision. The model is released under the apache‑2.0 license and offers a 262144 token context window.
Good at
- Reasoning tasks
- Tool integration
- Vision processing
Limits
- No vision support on CPU
- Large VRAM required for full context
- No mixture of experts
Best for
- Chatbots needing tool use
- Image captioning with context
- Developer prototyping
Who it’s for. Engineers and researchers who need a versatile model with reasoning, tool, and vision capabilities. The model is suitable for applications that can accommodate its memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 4.4 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 16.5 GB | 19.1 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 22.7 GB | 25.3 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quant file (4.43 GB, ~7.1 GB memory at 8k context). For 16 GB VRAM, choose the Q4_K_M 16.46 GB file (~19.1 GB memory). For 24 GB VRAM, the 22.66 GB Q4_K_M file (~25.3 GB memory) is recommended. Estimates are approximate.
What GPU do you need for Darkstar Harness?
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 Q8_0 (4.4 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 7.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 7.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 19.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (22.7 GB file, about 25.3 GB in use).
Which Darkstar Harness quant should you choose?
Q4_K_M is the usual starting point for Darkstar Harness: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 4.4 GB, about 0.3 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 Q8_0 at 4.4 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Darkstar Harness
How much VRAM does Darkstar Harness need?
About 19.1 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Darkstar Harness on an 8 GB GPU?
Yes, with Q8_0: the 4.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Darkstar Harness GGUF?
It depends on the quant: Q8_0 is 4.4 GB, Q4_K_M is 16.5 GB, Q4_K_M is 16.8 GB, Q4_K_M is 22.7 GB.
What context length does Darkstar Harness 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 Darkstar Harness GGUF?
The files are on Hugging Face in the SkylerMaxwell/Darkstar-Harness repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Darkstar Harness 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 Darkstar Harness on 8 GB VRAM?
Yes, using the Q8_0 quant file requires about 7.1 GB memory at 8k context, fitting within 8 GB VRAM.
Does Darkstar Harness support vision?
Yes, the model has detected vision abilities and can process image inputs.