LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio

Melvin Vivas · X post · 2026-09-19 · Open on X

Topics: Fine-tuning & Model Customization, Portfolio Projects · Level: intermediate

Summary

The creator fine-tuned Qwen3.5-2B with LoRA in Unsloth Studio, using his own popular tweets as the dataset. The model turns a topic or brief into an X post in his style. He shared it as a GGUF model on Hugging Face so you can run it locally in LM Studio.

Key points

• Base model: Qwen3.5-2B, a small model you can fine-tune on modest hardware.
• Dataset: the creator's own popular tweets, paired with topics/briefs as input and posts as output.
• Method: LoRA fine-tuning done in Unsloth Studio.
• Exported as GGUF so it runs locally in LM Studio.
• Use case: style transfer, turning topics and briefs into posts in one person's voice.
• Model repo: melvindave/qwen3.5-2b-melvin-posts-v1-GGUF on Hugging Face (the caption's link is cut off and returns a 404).

Resources mentioned

• qwen3.5-2b-melvin-posts-v1-GGUF (Hugging Face model) · repo · huggingface.co · free · open in a browser to verify
  The creator's LoRA fine-tune of Qwen3.5-2B in GGUF format, which writes X posts in his style.
• Qwen3.5-2B · tool · huggingface.co · free
  Small open-weight Qwen language model, used here as the base for fine-tuning.
  Also in: Post-training Qwen3.5-2B on your own X posts with Unsloth Studio (Melvin Vivas on X · notes), Fine-Tuned Qwen3.5-2B LoRA Model That Writes X Posts in Your Style (Melvin Vivas on X · notes), First LoRA Run on Qwen3.5-2B with Codex as Training Companion (Melvin Vivas on X · notes)
• Unsloth · tool · unsloth.ai · free
  Open-source library for fast, memory-efficient fine-tuning of open LLMs (LoRA/QLoRA) on a single GPU or in Colab.
  Also in: Run Laya Decision models locally with Unsloth on 4GB RAM (Melvin Vivas on X · notes), Unsloth passes 500M model downloads on Hugging Face (Melvin Vivas on X · notes), Run Qwen-Image-2.1 locally on 12GB VRAM with Unsloth GGUFs (Melvin Vivas on X · notes), Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes) and 29 more
• LM Studio · tool · x.com · free
  Desktop app for downloading and running LLMs locally, with a developer mode that serves models through an API.
  Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes), Post-training Qwen3.5-2B on your own X posts with Unsloth Studio (Melvin Vivas on X · notes) and 31 more

Try this

• Download the GGUF model from Hugging Face and run it in LM Studio.
• Fine-tune a small model (e.g. Qwen3.5-2B) with LoRA on your own posts so it writes in your voice.