Downloads · 30 days
172
5% of all-time downloads
texdata/Qwen3.6-35B-A3B-Slovenian-GGUF
Qwen3.6-35B-A3B-Slovenian-GGUF is a text generation model from texdata. Use it when you need the model to write or continue text. The card lists the license as other.
Trained by MediaAtlas — LLM fine-tuning on your own data, trained in the EU, weights delivered. Pricing · All our models
Downloads · 30 days
172
5% of all-time downloads
All-time downloads
3.3K
Public
Repo size
60.4 GB
Likes
3
Public
Click a slice to open those files.
.gguf60.4 GB · 100%
From the Hugging Face model README
Trained by MediaAtlas — LLM fine-tuning on your own data, trained in the EU, weights delivered. Pricing · All our models
Na kratko: Slovenski jezikovni model (35B MoE, 3B aktivnih) za pogovor, znanje in prevajanje EN ⇄ SL, z razmišljanjem. Glede na neuglašeno osnovo: slovenski nabor acc_norm 0,623 → 0,654, prevajanje BLEU EN→SL 23,8 → 26,3 in SL→EN 30,9 → 35,0; GGUF za llama.cpp in LM Studio. Sprejme tudi slike.
Vision / slike: takes images too. Load the mmproj-*.gguf next to the model (llama.cpp --mmproj; LM Studio pairs it automatically). Our training was text-only: image understanding is the base model's and was not evaluated in Slovenian.
Qwen/Qwen3.6-35B-A3B continued-pretrained + SFT for Slovenian (chat, knowledge, en↔sl
translation). Reasoning model. GGUF for LM Studio / llama.cpp.
On held-out evals vs the untuned base: Slovenian-LLM-Eval acc_norm 0.623 → 0.654; translation BLEU en→sl 23.8 → 26.3, sl→en 30.9 → 35.0.
| File | Size | Use |
|---|---|---|
qwen3.6-35b-a3b-slovenian-Q4_K_M.gguf | ~21 GB | recommended |
qwen3.6-35b-a3b-slovenian-Q8_0.gguf | ~38 GB | best quality |
mmproj-qwen3.6-35b-a3b-slovenian-F16.gguf | ~0.9 GB | vision (load alongside for image input) |
LM Studio: put the folder under ~/.lmstudio/models/<you>/, load the model.
mmproj file.llama.cpp:
llama-cli -m qwen3.6-35b-a3b-slovenian-Q4_K_M.gguf -p "Prevedi v slovenščino: Good morning!"
# vision:
llama-mtmd-cli -m ...-Q4_K_M.gguf --mmproj mmproj-...-F16.gguf --image slika.jpg -p "Opiši sliko."
Base Qwen/Qwen3.6-35B-A3B is Apache-2.0. CPT data is open-licensed → this repo is license: other:
| Data | License |
|---|---|
| Slovenian Wikipedia (CPT) | CC BY-SA 4.0 (attribution + ShareAlike) |
| FineWeb2 sl (CPT) | ODC-BY 1.0 |
Attribute the above CPT sources and comply with their terms before commercial use.
Cite this work (Tadej Fius, MediaAtlas Ltd):
@misc{fius2026qwen35bslgguf,
title = {Qwen3.6-35B-A3B Slovenian (GGUF)},
author = {Fius, Tadej},
year = {2026},
publisher = {MediaAtlas Ltd},
howpublished = {Hugging Face},
url = {https://huggingface.co/texdata/Qwen3.6-35B-A3B-Slovenian-GGUF}
}
Upstream / source citations:
@misc{qwen3, title={Qwen3 Technical Report}, author={{Qwen Team}}, year={2025}, url={https://huggingface.co/Qwen}}
@misc{wikipedia_sl, title={Slovenian Wikipedia}, author={{Wikimedia Foundation}}, note={CC BY-SA 4.0}, url={https://sl.wikipedia.org}}
@misc{penedo2024fineweb2, title={FineWeb2: A sparkling update with 1000s of languages}, author={Penedo, G. and others}, year={2024}, url={https://huggingface.co/datasets/HuggingFaceFW/fineweb-2}}
CPT data: Slovenian Wikipedia (CC BY-SA 4.0) and FineWeb2-sl (ODC-BY 1.0).