R_REDDYX.XYZ
AIPython★ 801⑂ 106 forksMIT

ARahim3/kaggle-tpu-lab

FREE TPU FOR QWEN3.8-27B

The kaggle-tpu-lab project runs Qwen3.8-27B (bf16) on a free Kaggle TPU, providing an OpenAI‑compatible API. It supports a 262k token context and ~130 tokens/s speed, works with Claude Code, Codex, Opencode and Pi.

// KEY FEATURES

  • OpenAI‑compatible endpoint for Qwen3.8-27B on a free Kaggle TPU.
  • Context window up to 262k tokens enables processing large files and repositories.
  • Generation speed ~130 tokens/s in bf16 precision delivers fast responses to agents.
  • Works with Claude Code, Codex, Opencode and Pi via standard OpenAI‑format requests.
#claude-code#coding-agents#free-gpu#jax#kaggle#llm-inference#llm-serving#long-context#openai-api#qwen#qwen3#speculative-decoding
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

AGENTSHIELD: AI AGENT SECURITY★ 801CHETAHCLAWS: AGENT HARNESS FOR AI★ 801DIGITAL AGENT SYRENE★ 801GPT-VIS: AI DATA VISUALIZATION★ 802MindFS FS for AI agents★ 799SWIFTLM: SWIFT LLM ON APPLE★ 799

← FULL CATALOG

ARahim3/kaggle-tpu-lab — Free Tpu For Qwen3.8-27b