AI & ML interests
Smaller open models for local deployment, tested against their originals. Built by TurinTech, creators of Artemis.
Recent Activity
TurinTech models
TurinTech models, built with algorithms found by our code optimisation platform called Artemis. GGUF and other versions of open models, with downloadable files, measured comparisons and runtime instructions on each model card.
Download compressed chat models
Compressed LLMs: Qwen3.5 and Qwen3.8, Gemma 4, Nemotron 3.5 Bolt, MiniCPM5, LFM3, GLM-5.2 and DeepSeek V4.1 Flash.
Download decision models
Compressed decision models: Cloudflare's Clef, Kev, Perplexity's pplx-decider, d3, Liquid AI's d1 and Mapika's decider-2b.
Download embedding models
Artemis
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? Ask on Discord or 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.
-
turintech/gemma-4-E4B-it-Artemis-GGUF
Image-Text-to-Text • 7B • Updated • 702k • 13 -
turintech/gemma-4-E2B-it-Artemis-GGUF
Image-Text-to-Text • 5B • Updated • 905k • 15 -
turintech/GLM-5.2-MaxMin108-GGUF
Text Generation • 325B • Updated • 2.92k • 13 -
turintech/Nemotron-3.5-Bolt-E4B-Artemis-GGUF
Text Generation • 8B • Updated • 9.02k • 13
-
turintech/gemma-4-E4B-it-Artemis-GGUF
Image-Text-to-Text • 7B • Updated • 702k • 13 -
turintech/gemma-4-E2B-it-Artemis-GGUF
Image-Text-to-Text • 5B • Updated • 905k • 15 -
turintech/GLM-5.2-MaxMin108-GGUF
Text Generation • 325B • Updated • 2.92k • 13 -
turintech/Nemotron-3.5-Bolt-E4B-Artemis-GGUF
Text Generation • 8B • Updated • 9.02k • 13