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: name the app Unsloth in the MCP settings copy (#13230)
a042876 Daniel Han committed 1 month ago
install.sh: install XPU PyTorch on Linux when an Intel Arc / Data Center GPU is the only GPU (#13193)
e31a080 Daniel Han committed 1 month ago
Unsloth Studio (AMD): pick a discrete GPU that fits over a larger APU in automatic GPU selection (#13196)
7d71eee Daniel Han committed 1 month ago
Studio: bound Qwen-Image-2.1 attention on Apple Silicon and fail loudly on NaN images (#13188)
dfffd23 Daniel Han committed 1 month ago
Studio: choose how often update notifications appear, including Unsloth updates (#13200)
4111181 Michael Han committed 1 month ago
Studio: show the installed Lemonade and FastFlowLM versions on the NPU (#13151)
38f3a61 oobabooga committed 1 month ago
Studio: fit MCP image mappings in the dialog and keep one field per tool (#13162)
a0a8f2e Etherl committed 1 month ago
Studio: list unsloth/Qwen-Image-2.1-Turbo-GGUF in the Images picker (#13206)
e0a9290 Daniel Han committed 1 month ago
Studio: treat a Smart App Control block of unsloth.exe like the AppLocker one (#13168)
05366bf oobabooga committed 1 month ago
Studio: cap sd.cpp threads at the cgroup CPU quota and honour UNSLOTH_CPU_THREADS (#13213)
88ff2ac Daniel Han committed 1 month ago
Studio: keep the composer expand button in the top corner when a file is attached (#13198)
f33fc6a Michael Han committed 1 month ago
Studio: give compare chat the same composer as normal chat (#13212)
93f1e7e Michael Han committed 1 month ago
Record the repo id for ModelScope loads so merged_16bit and GGUF export work (#13150)
554eb6b Daniel Han committed 1 month ago
Fall back to Unsloth inference for gpt-oss with fast_inference=True (#13155)
09ce386 Daniel Han committed 1 month ago
Studio: regenerate a chat's title from its latest turns (#13197)
8fc9395 Daniel Han committed 1 month ago
Studio: let @skill mentions work without Code and add bulk skill toggles (#13163)
d50286c Etherl committed 1 month ago
Studio: let small models send an attached image to a mapped MCP tool (#13166)
ebc8711 Etherl committed 1 month ago
Studio: keep HTML table rows together in knowledge bases and sources (#13186)
1a384c3 Nilay committed 1 month ago
Studio: show the whole conversation for imported Claude chats (#13182)
4ce8866 Nilay committed 1 month ago
Fix illegal memory access in block-FP8 LoRA kernels on long batches (#13141)
a0cd6ac Daniel Han committed 1 month ago
Studio: name the /v1/models VRAM-fit context estimate (#12599)
1b5e516 Aziz Muminov committed 1 month ago
Studio: turn on agent access (MCP) from Settings > API (#13167)
26de92c Etherl committed 1 month ago
Studio: train tool-calling datasets with their tool list (#13180)
a3afe32 Nilay committed 1 month ago
Studio: mount sidebar Recents a page at a time so long chat histories stay fast (#13165)
6ded031 oobabooga committed 1 month ago
Studio: send each line of a file attached in Chat with files once (#13179)
fd69020 Nilay committed 1 month ago
Fix case-sensitive Hugging Face projector pairing (#13161)
4e76159 Lee Jackson committed 1 month ago
Studio: stop cutting a fetched page down to one article element (#13178)
95728c9 Nilay committed 1 month ago