Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Dependencies: the studio extra carries usearch like studio.txt (#16176)
Daniel Han82ffe01be602
diff --git a/pyproject.toml b/pyproject.tomlindex f9b22cec777..b58fcc08bdb 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -168,6 +168,8 @@ studio = ["av>=12.3.0",# No win_arm64 wheel or sdist; RAG treats a missing sqlite_vec as unavailable."sqlite-vec==0.1.9 ; sys_platform != 'win32' or platform_machine != 'ARM64'",+ # Mirrors studio.txt: HNSW for gigantic RAG scopes, wheels for every target incl. win_arm64.+ "usearch==2.26.6",# Mirrors studio.txt: pymupdf publishes a win_arm64 wheel only for 1.28.2."pymupdf==1.27.2.3 ; sys_platform != 'win32' or platform_machine != 'ARM64'","pymupdf==1.28.2 ; sys_platform == 'win32' and platform_machine == 'ARM64'",