kaggle-tpu-lab
kaggle-tpu-lab is Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code.... It is ranked #549 on the Dev Radar, in Hosting & infra, first seen 2 days ago and shared in 1 post (4.5k views).
What people said about kaggle-tpu-lab on X
又有羊毛可以薅了。
— @m0d8ye, 2 days ago · 6 likes · see the post
Alternatives to kaggle-tpu-lab
- boat by ASCII — ascii box is now boat ( )
- Railway — Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin…
- qwen3.8-flash-next-single-dgx-spark — Qwen3.8-Flash-Next on ONE DGX Spark (TP=1). Contribute to MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark development by…
- Nebius Token Factory — Start building
- qwen3.8-flash-next-exl3-dgx-spark-recipe — Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with vLLM + vllm-exl3 -…
- Qwen-Omni — Qwen-Omni,Alibaba Cloud Model Studio:Use Qwen-Omni over HTTP to understand text, images, audio, and video. Choose…
kaggle-tpu-lab in numbers
- Rank on the Dev Radar: #549 of 1500
- Shared in 1 post by 1 account: @m0d8ye
- 4.5k views on those posts
- First seen 2 days ago, last shared 2 days ago
- Pricing seen by Jev: free
- Market: Hosting & infra
FAQ
What is kaggle-tpu-lab?
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code... It was first shared on X 2 days ago and is ranked #549 on the Dev Radar.
Is kaggle-tpu-lab free?
Yes, it is free to use.
Who shared kaggle-tpu-lab?
1 account on X, including @m0d8ye, in 1 post totalling 4.5k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 13.5k posts from 4.7k X accounts over the last 21 days, 1.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 19:24 UTC. Full method.