Running Qwen 3.5 35B Locally in LM Studio for Vision and Prompts

Melvin Vivas · X post · 2026-03-01 · Open on X

Topics: AI Dev Tools & Productivity, LLM Fundamentals, Prompt & Context Engineering · Level: beginner

Summary

The creator runs Qwen 3.5 35B locally in LM Studio and praises its vision ability. He uses it to write prompts for free instead of paying for API calls.

Key points

• Qwen 3.5 35B can run locally through LM Studio.
• Its vision (image understanding) is strong.
• Use case: write prompts (e.g., image prompts) locally at no cost.
• Local models cut API costs for routine tasks.

Resources mentioned

• 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), LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 31 more
• Qwen 3.5 35B · tool · huggingface.co · free
  An open-weight Mixture-of-Experts LLM from Alibaba's Qwen team that can run locally on a 24GB GPU.
  Also in: Local Qwen3.5-35B-A3B on a 24GB GPU Builds a Full Game From One Spec (Melvin Vivas on X · notes)

Try this

• Run Qwen 3.5 35B locally in LM Studio and use it to write prompts.