TurinTech models, built with Artemis. GGUF versions of open models, with downloadable files, measured comparisons and runtime instructions on each model card.
Compressed decision models: Clef, Kev, Perplexity Decider and d3. For structured decisions and answer probabilities, follow each card's tested /v1/systemone endpoint and settings.
Compressed LLMs: Qwen3.5, Gemma 4 and GLM-5.2. Browse the collection for published sizes and variants, with measured trade-offs on each card.
Embedding models: EmbeddingGemma 2 text embeddings with measured size and retrieval trade-offs. Follow the card’s tested CPU runtime and embedding API instructions.
Available native packages are listed on Ollama. Follow the model card for supported runtimes, recommended tags and run commands.
Built with Artemis, TurinTech's optimisation platform. Teams can use Artemis to make their own models smaller and faster, or to optimise their code. More at turintech.ai, or book a demo.
Questions, problems or a request for the next model to shrink? Reply in our feedback thread. More of our open-source work is at turintech.ai/open-source.
These are independent TurinTech releases, not affiliated with or endorsed by the original model authors. Each card links to its sources, credits and licence.