You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
Run open-weight LLMs (Qwen, GGUF, abliterated) on free Kaggle GPUs as a local OpenAI and Anthropic compatible API for Claude Code, opencode, Cursor and any OpenAI client. No local GPU needed.
Run VoiceStudio free on a Google Colab T4 GPU — voice cloning, video dubbing, TTS and transcription with zero local GPU. Remote-GPU setup for the open-source ElevenLabs alternative.
Headless Ollama tunneling tool for running 32B LLMs on Kaggle's dual T4 GPUs — with auth, VRAM locking, and a streaming kill switch. For personal AI research within Kaggle's usage policy.
Route GPU jobs from your terminal or your AI agent across free-tier clouds (Kaggle, Colab, Lightning, local MPS). One daemon, quota tracking, explained routing, Claude Code + Codex integration.
Turn Kaggle free T4x2 GPUs into an OpenAI-compatible image API - dual-GPU parallel, character consistency, 1080p/2K via upscaling, fixed Cloudflare domain. Zero cost.
Make talking AI-character reels for free: lip sync on Kaggle's free T4s (EchoMimicV3 / LatentSync), captions from your exact script, animated B-roll, music and SFX, one word-anchored project.json.