PSA: Qwen's Qwen-2.5-Coder-32B-Instruct is now live on Groq Inc for insanely fast (and smart) code generation. See below for instructions to add to Cursor.

1/4 Qwen2.5 Coder is state-of-the-art when it comes to coding capabilities for open-source models with impressive performance across several popular code generation benchmarks - even beating GPT-4o and Claude 3.5 Sonnet.

2/4 Beyond code generation, Qwen2.5 Coder with Groq speed is a game-changer for debugging workflows. Image Jon Skeet (famous for being top contributor on @StackOverflow) reviewing your code in real-time and helping you build, fix bugs, and ship fast. This is the dream (but real).

3/4 Ready to try on @cursor_ai? 1. Go to Cursor Settings 2. Go to Models 3. Override OpenAI Base URL with 4. Replace OpenAI with Groq API Key 5. Click "Add Model" and add qwen-2.5-coder-32b Now you have a smart + fast code assistant at your service. 🫡

4/4 More fast models. More to explore (or to act a lil silly and generate a silly lil Python game like I did). 🤝 Questions? Feature requests? Drop them below. We don't sleep (especially @omarkilani fr). Let's build something cool:

Is #x86 the New Mainframe - But Fading Much Faster? @intel @AMD @nvidia @Arm #AI #ARM #RISCV

@Alibaba_Qwen @GroqInc @cursor_ai Nice!

@Alibaba_Qwen @GroqInc @cursor_ai Groq speed + cursor Ai is 🔥

@Alibaba_Qwen @GroqInc @cursor_ai Nice! What context length?

@Alibaba_Qwen @GroqInc @cursor_ai 128K :)

@Alibaba_Qwen @GroqInc @cursor_ai How does it compare to Claude 3.5 Sonnet for coding?

@Alibaba_Qwen @GroqInc @cursor_ai we'll have a blog post out about this soon that i can share, but: - you can see some benchmarks at - try for yourself (the best benchmark for you is you)