GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

mradermacher/STARK-WEB-12B-GGUF overview

About < quantize version: 2 < output tensor quantised: 1 < convert type: hf < vocab type: < tags: < quants: x f16 Q4 K S Q2 K Q8 0 Q6 K Q3 K M Q3 K S Q3 K L Q4…

transformersggufcodetext-generationgemmahtmlcssjavascriptenplbase_model:Situus/STARK-WEB-12Bbase_model:quantized:Situus/STARK-WEB-12Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~4.50 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
1,273
Likes
0
Pipeline
text-generation

Repository Files & Downloads

11 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
STARK-WEB-12B.IQ4_XS.ggufGGUFGGUF6.23 GBDownload
STARK-WEB-12B.Q2_K.ggufGGUFGGUF4.50 GBDownload
STARK-WEB-12B.Q3_K_L.ggufGGUFGGUF6.12 GBDownload
STARK-WEB-12B.Q3_K_M.ggufGGUFGGUF5.67 GBDownload
STARK-WEB-12B.Q3_K_S.ggufGGUFGGUF5.15 GBDownload
STARK-WEB-12B.Q4_K_M.ggufGGUFGGUF6.87 GBDownload
STARK-WEB-12B.Q4_K_S.ggufGGUFGGUF6.54 GBDownload
STARK-WEB-12B.Q5_K_M.ggufGGUFGGUF7.96 GBDownload
STARK-WEB-12B.Q5_K_S.ggufGGUFGGUF7.77 GBDownload
STARK-WEB-12B.Q6_K.ggufGGUFGGUF9.11 GBDownload
STARK-WEB-12B.Q8_0.ggufGGUFGGUF11.80 GBDownload

Model Details

Model IDmradermacher/STARK-WEB-12B-GGUF
Authormradermacher
Pipelinetext-generation
Licenseapache-2.0
Base modelSituus/STARK-WEB-12B
Last modified2026-06-24T10:30:26.000Z

Model README

---

base_model: Situus/STARK-WEB-12B

language:

  • en
  • pl

library_name: transformers

license: apache-2.0

mradermacher:

readme_rev: 1

quantized_by: mradermacher

tags:

  • code
  • text-generation
  • gemma
  • html
  • css
  • javascript

---

About

<!-- ### quantize_version: 2 -->

<!-- ### output_tensor_quantised: 1 -->

<!-- ### convert_type: hf -->

<!-- ### vocab_type: -->

<!-- ### tags: -->

<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->

<!-- ### quants_skip: -->

<!-- ### skip_mmproj: 1 -->

static quants of https://huggingface.co/Situus/STARK-WEB-12B

<!-- provided-files -->

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/STARK-WEB-12B-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's

READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for

more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |

|:-----|:-----|--------:|:------|

| GGUF | Q2_K | 4.9 | |

| GGUF | Q3_K_S | 5.6 | |

| GGUF | Q3_K_M | 6.2 | lower quality |

| GGUF | Q3_K_L | 6.7 | |

| GGUF | IQ4_XS | 6.8 | |

| GGUF | Q4_K_S | 7.1 | fast, recommended |

| GGUF | Q4_K_M | 7.5 | fast, recommended |

| GGUF | Q5_K_S | 8.4 | |

| GGUF | Q5_K_M | 8.6 | |

| GGUF | Q6_K | 9.9 | very good quality |

| GGUF | Q8_0 | 12.8 | fast, best quality |

Here is a handy graph by ikawrakow comparing some lower-quality quant

types (lower is better):

!image.png

And here are Artefact2's thoughts on the matter:

https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to

questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting

me use its servers and providing upgrades to my workstation to enable

this work in my free time.

<!-- end -->

Run mradermacher/STARK-WEB-12B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models