unsloth-gguf
Unsloth provides a streamlined method to export fine-tuned models directly to GGUF format. It features "Dynamic 2.0" quantization, which protects sensitive weights to maintain high accuracy, and automates the merging of LoRA adapters.
Profile →npx skills add majiayu000/claude-skill-registry --skill unsloth-gguf-cuba6112-skillfactory-c22932b8 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: unsloth-gguf description: Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf, quantization export, llama.cpp, ollama, save_pretrained_gguf, modelfile. --- ## Overview Unsloth provides a streamlined method to export fine-tuned models directly to GGUF format. It features "Dynamic 2.0" quantization, which protects sensitive weights to maintain high accuracy, and automates the merging of LoRA adapters. ## When to Use - When deploying models to local serving platforms like Ollama, llama.cpp, or LM Studio. - When model size needs to be minimized for CPU-based inference or low-VRAM GPUs. - When sharing models with the community via GGUF format. ## Decision Tree 1. Is target VRAM very low? - Yes: Use `quantization_method = 'q4_k_m'` or higher compression. - No: Use `q8_0` or `f16` for maximum quality. 2. Deploying to Ollama? - Yes: Export to GGUF and then create a `Modelfile` with a `FROM` command. ## Workflows ### Exporting Fine-tuned Models to GGUF 1. After training, call `model.save_pretrained_gguf("name", tokenizer, quantization_method='q4_k_m')`. 2. Specify quantization method (e.g., `q4_k_m`, `q8_0`, `f16`
- Overview
- When to Use
- Decision Tree
- Workflows
- Exporting Fine-tuned Models to GGUF
- Deploying to Ollama
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the unsloth-gguf skill do?
Unsloth provides a streamlined method to export fine-tuned models directly to GGUF format. It features "Dynamic 2.0" quantization, which protects sensitive weights to maintain high accuracy, and automates the merging of LoRA adapters.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill unsloth-gguf-cuba6112-skillfactory-c22932b8 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.