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
Commits on main
Studio: keep Switch Back visible for a snapshot-path chat (#10511)
56aa1e1 Chaitanya Laxman committed 1 month ago
Track the pinned upstream UEmbed reference behind the parity test (#9324)
09cde92 JAESOL SHIN committed 1 month ago
Add the UEmbed unified training loss and its fine-tuning scripts (#9323)
d07d9f0 JAESOL SHIN committed 1 month ago
Fix import UnicodeDecodeError from subprocess output (#9704)
ae1b274 chensimian committed 1 month ago
studio: add keyboard shortcuts for UI zoom and scaling (Cmd/Ctrl + / - / 0) (#9647)
2070d24 brickheadbs-claude committed 1 month ago
Studio: bound repeated llama-server respawns after SIGKILL (#9689)
007fe81 Julien BODIN committed 1 month ago
Don't reuse a leftover incomplete isolated Node tree (#9361)
2bc9991 adam siwiec committed 1 month ago
Wire UEmbed offset pooling and SPLADE sparse output into FastSentenceTransformer (#9322)
c698f08 JAESOL SHIN committed 1 month ago
Document sharing models and projects across login users (#9363)
46cb6b6 adam siwiec committed 1 month ago
Windows: keep uv cache under the Studio root (superseded by main) (#9007)
a0bd1f1 Max-Reisinger committed 1 month ago
Studio: delete the models Studio only discovered, support files included (#9313)
b18b6bf Atharv Sharma committed 1 month ago
Studio: stop the SWA config probe from adding a phantom base model and refetching every load (#10607)
095e664 Chaitanya Laxman committed 1 month ago
Studio: show the eject toast before the running-chats check (#10469)
e157f09 Chaitanya Laxman committed 1 month ago
Studio: load S3 audio datasets by downloading the audio beside its manifest (#10050)
95421ed Shubhankar Tripathy committed 1 month ago
feat(studio): type-to-activate search, composer and prompt inputs (#10303)
2fd457b Fahad Iftikhar committed 1 month ago
Studio: search, sort, multi-select and collapse for project sources (#8850)
09f3c56 Rafael Oliveira committed 1 month ago
fix(install): route Linux Intel GPU hosts away from CPU-only torch (#5274)
26db015 William Obino committed 1 month ago
studio: install torchcodec from the PyTorch cuXXX index on Linux aarch64 (#4456)
8b4a959 vivek varikuti committed 1 month ago
Studio: mention the leftover uv cache in uninstall (#10442)
f4bf6c5 Chaitanya Laxman committed 1 month ago
fix: pass force_download through to snapshot_download in _get_statistics (#8906)
660c86a Arthi Arumugam committed 1 month ago
Studio: reasoning effort slider, LM Studio provider, project folder (superseded) (#8970)
858c703 Mirin committed 1 month ago
Fix connected/cloud Max Tokens fallback for MiniMax M3 (#8914)
eca46d2 Aizen__28 committed 1 month ago
Fix attention support detection for trust_remote_code models (#8229)
b46bd53 Shaurya committed 1 month ago
feat: add Gefen-X (gefenx / gefenx_muon) optimizer integration (#7051)
0dface5 thad0ctor committed 1 month ago
Phi-4-multimodal-instruct support (null contribution) (#4278)
d938442 Rishabh Dewangan committed 1 month ago
docs: add 4GB VRAM QLoRA fine-tuning guide for consumer GPUs (#7605)
88ff14c Dante committed 1 month ago