Technology · LLMs → Fine-tuning · Open Core · wiki:stub
This pack is still a wiki stub. Opening text below if present; full article bands appear after deepen (`Wiki-status: deep`).
Unsloth accelerates LoRA/QLoRA fine-tuning with memory/speed optimizations (open-core). Shortens the loop for custom model experiments. Use in the model factory beside Axolotl/HF trainers when iteration speed on adapters matters. Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Unsloth Start connects Claude Code, Codex and other agents to local models with one command. bash unsloth start claude --model unsloth/Qwen3.8-27B-GGUF:UD-Q4KXL | Claude Code | unsloth start claude | | OpenAI Codex | unsloth start codex | | DeepSeek Harness | unsloth start dsh | | Hermes Agent | unsloth start hermes | | OpenCode | unsloth start opencode | | OpenClaw | unsloth start.
9 tags · 6 out · 7 in · 3 artifacts · 1 gaps · 13 corpus docs
map_edge · 4
tech_features · 1
tech_quote · 7
tech_readme · 1