Reading the repo — stats and the shipped feed land in about ten seconds…
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
77.3k 7.1k 890 openLast shipped 2h ago
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
The week brought substantial additions to Studio's audio capabilities, with new dedicated pages for voice cloning, speech editing, music production, audio conversion, and transcription—each with features like stem mixing, A/B comparison, and speaker tracking. In parallel, the team optimized…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in unsloth's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
Frontend test: give the cold Vite SSR render in reasoning-source-render room on a loaded runner (#12903)
Studio: continue searching past unusable results and add a Wikipedia fallback (#12892)
Studio: keep browser panel tooltips, toasts and menus visible over desktop web pages (#12895)
Sandbox test: wait for the cache scan workers before counting them (#12896)
Support every PEFT init_lora_weights option, with fast PiSSA and MiCA init (#6879)
Baseline the eight unsloth-zoo 2026.10.1 findings after review (#12884)
Studio: fill the Hebrew and Swedish strings that left the strict i18n check red on main (#12881)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
