STARK WEB 12B v1.7 needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma4 12B model for UI/UX design and frontend coding
STARK WEB 12B v1.7 is a 11.9B parameter model fine‑tuned on Gemma 4 12B. It targets single‑file dashboards, canvas games and responsive tools with a 9‑step chain‑of‑thought reasoning process. The model was trained on ~16 million tokens and supports coding and vision.
Good at
- coding
- vision
- UI/UX design
Limits
- requires >18 GB VRAM for 8 k context
- licensed under apache‑2.0
- limited language support (~90 % English, ~10 % Polish)
Best for
- single‑file dashboards
- canvas games
- responsive UI tools
Who it’s for. Developers and designers who need a local model to generate web interfaces and frontend code. The model is suitable for teams that prefer open‑source solutions and can provide the necessary GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For a 8 k context, the smallest quant is Q2_K with a file size of 4.83 GB and an estimated memory of 18.2 GB. If you have at least 20 GB VRAM, Q4_K_M (7.38 GB, 20.8 GB memory) is a good balance. For higher fidelity, Q8_0 (12.67 GB, 26.1 GB memory) is available but requires the largest memory budget.
What GPU do you need for STARK WEB 12B v1.7?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which STARK WEB 12B v1.7 quant should you choose?
Q4_K_M is the usual starting point for STARK WEB 12B v1.7: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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 Q2_K at 4.8 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 STARK WEB 12B v1.7
How much VRAM does STARK WEB 12B v1.7 need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 STARK WEB 12B v1.7 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of STARK WEB 12B v1.7 GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_S is 7.0 GB and 5 more.
What context length does STARK WEB 12B v1.7 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download STARK WEB 12B v1.7 GGUF?
The files are on Hugging Face in the mradermacher/STARK-WEB-12B-v1.7-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 STARK WEB 12B v1.7 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 this model on 8 GB VRAM?
No, the model requires more than 18 GB VRAM for 8 k context.
Does it support Polish language?
Yes, it supports approximately 10 % Polish alongside English.
Is vision support available?
Yes, the model has vision capability as part of its detected abilities.