Dirk Qwen3.8 27B needs about 16.9 GB of memory at IQ4_XS (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.8 GB (IQ2_XS) to 31.5 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Dirk Qwen3.8 27B – a dense vision‑language model with 27.3B parameters
Dirk is a 27.3B parameter Qwen3.8 model that includes a vision encoder. It supports image and video understanding and is optimized for lean, on‑task responses. The model is released under the apache‑2.0 license.
Good at
- Vision‑language tasks
- Long‑horizon agentic planning
- Coding and professional work
Limits
- No built‑in vision support in some runtimes
- Large VRAM requirement for higher‑quality quants
- Requires a 262144 token context for full capability
Best for
- Image‑guided code generation
- Multistep reasoning with visual context
- Video analysis and summarization
Who it’s for. Developers and researchers who need a compact vision‑language model for inference on local hardware. The model is suitable for integration into existing LLM stacks via llama.cpp or other GGUF‑compatible runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 8.8 GB | 11.5 GB | Too big | Get file → | |
| IQ2_S | 9.6 GB | 12.3 GB | Too big | Get file → | |
| Q2_K_XL | 9.8 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XXS | 10.4 GB | 13.1 GB | Too big | Get file → | |
| IQ3_S | 12.1 GB | 14.8 GB | Too big | Get file → | |
| Q3_K_XL | 13.1 GB | 15.8 GB | Too big | Get file → | |
| IQ4_XS | 14.3 GB | 16.9 GB | Too big | Get file → | |
| Q4_K_S | 15.4 GB | 18.0 GB | Too big | Get file → | |
| Q4_K_XL | 17.6 GB | 20.2 GB | Too big | Get file → | |
| Q5_K_XL | 20.9 GB | 23.6 GB | Too big | Get file → | |
| Q6_K | 22.0 GB | 24.7 GB | Too big | Get file → | |
| Q6_K_XL | 25.3 GB | 28.0 GB | Too big | Get file → | |
| Q8_K_L | 28.0 GB | 30.7 GB | Too big | Get file → | |
| Q8_K_XL | 31.5 GB | 34.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (8.77 GB) or IQ2_S (9.61 GB). For 16 GB VRAM, Q4_K_S (15.36 GB) or Q4_K_XL (17.56 GB) provide a balance of size and performance. For 32 GB VRAM, Q6_K_XL (25.3 GB) or Q8_K_XL (31.46 GB) give the highest quality.
What GPU do you need for Dirk Qwen3.8 27B?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_XS (8.8 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_XL (13.1 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_XL (20.9 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_K_L (28.0 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (31.5 GB file, about 34.1 GB in use).
Which Dirk Qwen3.8 27B quant should you choose?
IQ4_XS (14.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_XS at 8.8 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 Dirk Qwen3.8 27B
How much VRAM does Dirk Qwen3.8 27B need?
About 16.9 GB at IQ4_XS with an 8K context window. That is the 14.3 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 Dirk Qwen3.8 27B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Dirk Qwen3.8 27B GGUF?
It depends on the quant: IQ2_XS is 8.8 GB, IQ2_S is 9.6 GB, Q2_K_XL is 9.8 GB, IQ3_XXS is 10.4 GB, IQ3_S is 12.1 GB, Q3_K_XL is 13.1 GB and 8 more.
What context length does Dirk Qwen3.8 27B 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 Dirk Qwen3.8 27B GGUF?
The files are on Hugging Face in the blackfan23/Dirk-Qwen3.8-27B-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 Dirk Qwen3.8 27B 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 Dirk on 8 GB VRAM?
Yes, the IQ2_XS quant is 8.77 GB and requires about 11.5 GB of VRAM at 8 k context.
Does Dirk support vision tasks?
Yes, Dirk includes a vision encoder and can process images and videos.
What license does Dirk use?
Dirk is released under the apache‑2.0 license.