While other coding agents are busy turning tokens into invoices, Junie focuses on getting the job done. AI coding agent by @jetbrains

It was a fun experience to play with RTX Spark laptops! They are more powerful than the M5 Max in terms of compute, but memory speed is a bit slower.
Your GPU. Your code. No token bill. Junie Local runs on NVIDIA RTX Spark from day one. Windows support is stable, too. Reads code. Edits files. Runs tests. All locally. Try it free → junie.jetbrains.com/blog/jun…
1
2
147
I’m already working on more optimizations and custom models for @NVIDIARTXSpark Local inference is so fun and full of ideas to be implemented
Junie Local now runs on @NVIDIARTXSpark from day one. Get a full-fledged coding agent on your PC. It reads your code, edits files, and runs tests. There are no tokens or quotas, and no code leaves the machine. Windows support is stable, too. All you need is a 24 GB Nvidia RTX card. Try it for free: junie.jetbrains.com/local
2
8
205
Gemini 4 Argon has landed in Junie CLI and @getsome_air 😎
10
422
Your GPU. Your code. No token bill. Junie Local runs on NVIDIA RTX Spark from day one. Windows support is stable, too. Reads code. Edits files. Runs tests. All locally. Try it free → junie.jetbrains.com/blog/jun…
Made with AI
2
17
718
Thank you @NVIDIAAI for giving us the opportunity to bring day-one support for @junie_ai Local on @NVIDIARTXSpark! What I personally like the most about RTX Spark is that provides enough memory to run BOTH local AI experiments and local coding agents at the same time, all using the same CUDA stack that I use in prod Here’s a screenshot of me asking Junie Local to run an SLM pretrain experiment - both are running on the same RTX Spark!
NVIDIA RTX Spark is here. Build AI locally, bring your creative ideas to life, and take your favorite games along. A new beginning for @Windows PCs starts today.
1
2
11
404
Junie retweeted
Try agentic coding with JetBrains Air and Junie Lite for free in PyCharm 2026.3 EAP 4 👇
Free, fast, and private agentic coding inside PyCharm? JetBrains Air is live in PyCharm 2026.3 EAP 4, and you can test it for free with Junie Lite – simply sign in with your JetBrains Account. No paid AI subscription required! 🤖 Powered by open-weights Qwen 3.6 27B + JetBrains code intelligence 🔒 Private by design – your code is never used for training ⚡ Perfect for routine tasks, boilerplate, and test generation in Air.
1
3
54
7,256
Junie retweeted
Announcing 20 new MCP partners at Config India (!!) Amp, ClickUp, Dia, Junie by JetBrains, Linear, Meta Muse, Mistral, Notion, OpenCode, Sarvam Agents, Agentforce Vibes, Amazon Quick, Amplitude Wave, Cline, Delta, Dust, Glass, Gradial, Writer, Zed, Microsoft 365 Copilot
40
65
1,518
9,661,063
👀
14
631
Haiku 5.5 is now in Junie 😎
1
14
694
Junie retweeted
How to use @junie_ai in Air at no charge: 1. Install the Air plugin for your IDE 2. Choose the Lite model for Junie 3. Have fun
2
6
70
6,205
Your backlog just got a free coding agent. Meet Junie Lite, powered by Qwen 3.6 27B in the cloud. Now in the CLI and JetBrains IDEs via Air. Free for now with your JetBrains Account. blog.jetbrains.com/ai/2026/1…
2
4
40
3,312
Junie retweeted
Big Day for @jetbrains IDEs and for @junie_ai . A completely new agentic experience is open today in our IDEs - we call it JetBrains Air. And the best part - Junie provides free baseline intelligence tier - Junie Lite. In JetBrains Air you have a professional control plane over your agents (plug-in any agent you already love), agents work in parallel, you can link sessions with each other, delegate inline comments from code or md files to agents and many more. Read the details here: blog.jetbrains.com/ai/2026/1…
1
2
4
359
Junie retweeted
Replying to @junie_ai
@junie_ai team is attending Gemini 4 Argon evaluation workshop. The latest model from @GoogleDeepMind
1
2
157
Sonnet 5.5 yesterday. GPT-6.1 Sol today. Both in Junie. Good luck picking a favorite 😏
2
5
22
855
Sonnet 5.5 is already in Junie 😎
13
531
Same bug. Who fixes it first? Now in Junie: Grok 4.7, Claude Opus 5.5, GPT-6 Sol & Luna.
Made with AI
1
14
783
Last call for Gemini 3.8 Flash at 75% off in Junie. The doors are closing. That app you were going to finish “later”? This is later. junie.jetbrains.com/blog/jun…
8
677
Why does Junie Local on Mac start at M5 today? Our engineers estimate M5 has ~2–3× M4's compute. Processing code and tool output takes real work. Generation speed also varies with MTP's hit rate. We're tuning for the whole coding session. 🧵
3
1
13
893
And why 64GB? Our coding sessions use ~40–120K context tokens, with tool use. Model weights, context cache, runtime and your IDE all share memory. We need room for the whole coding session. The weights have roommates.
1
6
317
Junie runs 4-bit models: • Mac: MLX 4-bit • Windows preview: GGUF Q4_K_M (RTX Ampere+, 24GB+ VRAM) Want to tinker? BF16, MLX and GGUF weights are public, with setup instructions: huggingface.co/collections/J…
1
6
185