Replit Code V1.5 3B

What it does

Replit Code v1.5 is a 3.3B parameter Causal Language Model focused on Code Completion. The model is trained in bfloat16 on 1T tokens of code (~200B tokens over 5 epochs, including linear cooldown) for 30 programming languages

• 
  repl.it2015 · ▲109

  Online code repl for pretty much any language.

• 
  Repl.it Teams for Education2021 · ▲145

  Zero-setup collaborative cloud IDE for teachers and students

• 
  Qwen3-Coder2025 · ▲248

  A powerful open model for agentic coding tasks

• 
  Qwen3.6-35B-A3BApr 2026 · ▲124

  The open sparse MoE model for agentic coding

• 
  Mistral Medium 3.5Apr 2026 · ▲123

  A 128B model for coding, reasoning, and long tasks

• 
  Qwen3.6-27BApr 2026 · ▲120

  The sweet-spot open dense model for coding agents

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

  AI · 17d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

  AI · 26d ago · cactuscompute.com

• 
  Coldtea.ai▲512

  Make your software self-driving

  AI · 30d ago · coldtea.ai

• 
  Soloop▲472

  Approval-first Agent OS for solo founders

  AI · 30d ago · soloop.io

• 
  AI Content Genie▲1,073

  AI autopilot for content creation & marketing

  AI · 2023 · typeface.ai

• 
  Nudge 2.0▲1,051

  In-app experiences to activate, retain, & understand users

  Growth · 2023 · nudgenow.com

• 
  Cal.ai Email Assistant▲918

  World's first open source AI scheduling assistant

  AI · 2023 · cal.com

• 
  Design Studio by Tiledesk▲866

  Unlock AI magic for elevated customer engagement, fast

  AI · 2023 · tiledesk.com

• 
  TalkNotes▲854

  Turn your thoughts into actionable notes, fast

  AI · 2023 · talknotes.io

• OD
  OpenAPI DevTools – Chrome extension that generates an API spec▲811

  Effortlessly discover API behaviour with a Chrome extension that automatically generates OpenAPI specifications in real time for any app or website.

  Dev tools · 2023 · github.com