I replaced my ChatGPT subscription with a local AI coding tool and haven't looked back
… Plugging Qwen into VS Code via the Continue extension is what made me realize how powerful local AI can be . …
Search
Tracked topic
Alibaba
Live now
Alibaba might release a new open image model Swift-Image 6B
I gave a local LLM control of my entire homelab, and nothing ever touched the cloud
… Qwen 3.5 4B handles most of the routine work It supports tool calling and is small enough to run alongside Ollama I evaluated a bunch of local LLMs here, but ended up using Qwen 3.5 4B. …
I ditched Claude Code's $20 plan for a local LLM in VS Code, and I'm getting more done
… After installing the extension, just add the local model to ~/.continue/config.yaml: - name: Qwen2.5 Coder 14B provider: openai model: ai/qwen2.5-coder:14B apiBase: http://localhost:12434/engines/v1 apiKey: not-needed contextLength: 8192 maxTokens: 2048 temperature: 0.1 capabilities: - tool use rol… …
I gave Qwen 3.6 a real coding task on my RTX 5080, and now I barely open Claude
… All I did was open PowerShell, install Ollama, pull the model, and set two parameters to optimize performance: winget install ollama ollama pull qwen3.6:35b ollama run qwen3.6:35b --verbose /set parameter num ctx 65536 /set parameter temperature 0.6 There's a lot more configuration you could do to … …
I replaced ChatGPT with a local model on my gaming PC, and it's beating the cloud where I didn't expect
… I run it locally and expose it to Qwen 3.6 27B as an MCP server, so the model can search the web, pull in fresh information, and reason over it the same way ChatGPT does with its browsing tool. …
I don't need Claude, this is the local LLM I run on my NAS that powers my smart home
… For most smart homes, you don't need Claude, but a local model that's realistic for your hardware, and Qwen 2.5 fits that role well. Qwen Qwen is a comprehensive family of advanced large language models LLMs and large multimodal models LMMs . …
I tested a local LLM against a frontier cloud model, and the gap was smaller than I expected
… In one test, with 90,000 tokens of context and zero contamination, the local model gave the better answer. This isn't local models beating the cloud, because they don't overall . It's messier than that, but Qwen gives it some fantastic competition. …
The biggest local LLM on your machine is useless if it can't call a single tool, no matter how many parameters it has
… I used to run Qwen 3 Coder Next all the time, but now I run Qwen3.6 27B on my 7900 XTX and Qwen3.6 35B A3B on my MacBook Pro and Lenovo ThinkStation PGX, and all of them have been the most reliable tool-callers I've used locally. …
I ran my local LLM for hours and watched it get dumber in real time
… Your local LLM isn't actually dumber, but how you're using it is The degradation in performance of local LLMs over time is due to multiple factors working together. …
I connected my local LLM to my browser and it changed how I automated tasks
… This runs a local API at http://localhost:11434, which is what everything else talks to. Once that’s running, you need to pull a model. In my case, I used Qwen, so something like ollama pull qwen:7b works well for a balance between performance and capability. …