Repository
ARahim3/kaggle-tpu-lab
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.
Stars
678
Today
+9
last 24 hours
This week
+9
Forks
93
Clone
git clone https://github.com/ARahim3/kaggle-tpu-lab.gitStar growth
#claude-code#coding-agents#free-gpu#jax#kaggle#llm-inference#llm-serving#long-context#openai-api#qwen
- Created
- 2026-08-31
- Last commit
- 2026-10-06
- Gained since tracking
- +9
Updated Sun, 18 Oct 2026 15:32:30 GMT · description from the project itself