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 the sidebar's bottom fade in step with the list (#12423)
f864051 Michael Han committed 1 month ago
unsloth start pi: add --max-tokens to set Pi's output token limit (#12393)
c3eef76 Lee Jackson committed 1 month ago
Stop the model selector's format and quant suffix clipping descenders (#12427)
1a96706 Daniel Han committed 1 month ago
Studio: make Compare in Chat load the full fine-tune that just finished (#12380)
6c7f044 Nilay committed 1 month ago
Studio: keep Word footnotes and endnotes in chats and knowledge bases (#12378)
f000412 Nilay committed 1 month ago
Studio: faster MiniMax-H3 GGUF renders (resident under memory auto, sd.cpp pin upgrade, speed_mode=max kernels) (#12405)
c85ee37 Daniel Han committed 1 month ago
Studio: remove the white seam above the chat panel on Windows dark mode (#12425)
b1f03a1 Daniel Han committed 1 month ago
Keep an explicit HF_HUB_ENABLE_HF_TRANSFER and install hf_transfer in Core CI (#12394)
ecb5c46 Daniel Han committed 1 month ago
Studio: keep the arrow cursor on a sent prompt's time (#12420)
3b579a6 Michael Han committed 1 month ago
Studio: remove the Projects section setting from Chat settings (#12421)
792f815 Michael Han committed 1 month ago
Studio: always show composer attachments as cards, rename sent layouts (#12418)
3532764 Michael Han committed 1 month ago
Fix desktop icon clarity with supplied artwork and Tauri resource icons (#12352)
11839e6 Wasim Yousef Said committed 1 month ago
Stop conversation_extension crashing when the caller keeps their columns (#8373)
5eb891e Vineeth Sai Varikuntla committed 1 month ago
Studio: smaller scroll to bottom button, visible in dark mode, with a setting to hide it (#12417)
747ec43 Michael Han committed 1 month ago
Studio: warn that a Web share link from a remote Studio exposes its address (#12413)
1422bfc Daniel Han committed 1 month ago
Studio: stop the backend crashing on startup when memory is tight (#12374)
1c4b92c Nilay committed 1 month ago
Studio: fix PDF previews after a PDF attachment is extracted (#12346)
864fc1d Michael Han committed 1 month ago
Restore full-rank gradients after Q-GaLore updates (#10878)
48ab67f Vineeth Sai Varikuntla committed 1 month ago
Studio: keep Qwen-Image-2.1 image conditioning finite on ROCm (#12360)
0e2df89 oobabooga committed 1 month ago
Studio: continue finished replies and resume GGUF reasoning (#12371)
1250bf1 oobabooga committed 1 month ago
fix(studio): keep scoped download progress tied to current files (#12390)
543acd5 Lee Jackson committed 1 month ago
Treat {{ and }} in a merged prompt as literal braces (#10742)
fc84dd1 Vineeth Sai Varikuntla committed 1 month ago
Keep the MLX adamw_8bit optimizer instead of collapsing it to adamw (#9950)
49b2ff9 Vineeth Sai Varikuntla committed 1 month ago
Studio: let the Decision API use TypeSafe, Liquid AI, OpenRouter and other System One servers (#12373)
193c8da Nilay committed 1 month ago
Studio: keep a local model's built-in system prompt when the date setting is on (#12382)
101b2d6 Nilay committed 1 month ago
Stop the Chat UI persisted-monitor reset from running script in the stale page (#12412)
d2528e6 Daniel Han committed 1 month ago
Studio: say Pin in model menus, and drop the border on sidebar right-click submenus (#12414)
fa0e025 Michael Han committed 1 month ago
Seed preview: check path-backed image cells against the account's workspace (#12404)
c0a6044 Daniel Han committed 1 month ago
Compare Kaggle reference repo ids without case and prefetch the Qwen3 4bit repo under its new spelling (#12411)
eba095f Daniel Han committed 1 month ago