Running Qwen 3.5 locally with Claude Code on an RTX 3090
Melvin Vivas · X post · 2026-03-05 · Open on X
Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: intermediate
Summary
The creator reports that the open Qwen 3.5 model runs on a consumer RTX 3090 GPU with 24 GB of VRAM. He says it works well as the model behind Claude Code and can use agent skills. This suggests local open models are now a workable option for agentic coding.
Key points
- Qwen 3.5 can run locally on an RTX 3090 with 24 GB VRAM
- Qwen 3.5 works well when connected to Claude Code
- The local model can use Claude Code skills
- A consumer GPU is enough for local agentic coding
Resources mentioned
- Qwen 3.5 · tool · qwen.ai · free
Alibaba Qwen open model family with small on-device variants and toggleable reasoning.
Also in: Train Your Own Decision Model Locally with Unsloth (Melvin Vivas on X · notes), Workshop AI: Building Apps with Cloud and Local Agents (GLM 5, Qwen 3.5) (Melvin Vivas on X · notes), Qwen3.5 0.8B Does Real-Time Local Video Captioning (Melvin Vivas on X · notes), Qwen3.5 0.8B Real-Time Video Captioning on Mac Studio (Melvin Vivas on X · notes) and 8 more - Claude Code · tool · code.claude.com · paid · recommended by both Bashiri Smith & Melvin Vivas
Build agents and pipelines from the terminal; the guide's main agentic coding tool.
Also in: First impressions: Claude Code in the cloud is good and fast (Melvin Vivas on X · notes), Why Claude Code feels faster: gzipped turns and instant cloud sessions (Melvin Vivas on X · notes), Watch What Fills Your Coding Agent's Context and When to Clear (Melvin Vivas on X · notes), Claude Code's Right Sidebar and Context Breakdown (Melvin Vivas on X · notes) and 124 more - NVIDIA GeForce RTX 3090 · tool · nvidia.com · paid
A consumer GPU with 24 GB of VRAM, used as the local hardware for image and video generation.
Also in: Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes), Grok as "Director": Making a Local Anime Clip with ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Making a 40-Second Anime Episode Locally with ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Local $0 Video Head Swap: MiniMax H3 Ref2VA (INT8) + LoRA in ComfyUI (Melvin Vivas on X · notes) and 6 more
Try this
- Consider buying a GPU with 24 GB VRAM to run local models
- Try connecting a locally hosted Qwen 3.5 to Claude Code
- Set up a local coding agent: Qwen 3.5 served on your own GPU and driven by Claude Code with skills
More in AI Dev Tools & Productivity
- Kling Video 3.0 Motion Control Is Available on fal
- OpenAI Codex App Now Available on Windows
- Kling Motion Control 3.0: Motion Capture with Better Facial ID Consistency
- v0 vs Claude Code for cloning an app's design
- When one coding model gets stuck, switch to another
- 35% of PRs Are Coded by Cursor's Autonomous Agents