OSS Radar
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)… Why it matters: relevant if AI is part of your coding workflow.
GitHub description: 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
624
Last 24h
+14est.
Last 7 days
+101est.
Forks
87
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Not enough history yet. OSS Radar records stars every hour, so this chart fills in over the next few hours.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/ARahim3/kaggle-tpu-lab)<a href="https://ossradar.net/repo/ARahim3/kaggle-tpu-lab"><img src="https://ossradar.net/badge/ARahim3/kaggle-tpu-lab" alt="Trending on OSS Radar"></a>About kaggle-tpu-lab
ARahim3/kaggle-tpu-lab is a Python project in the Coding agents category, created 43 days ago. It has 624 GitHub stars and 87 forks, and gained +101 stars over the last 7 days (early estimate), ranking #9 of 71 Coding agents repos tracked by OSS Radar this week.
See more trending Coding agents repos or the top AI repos this week.
- Language
- Python
- Category
- Coding agents
- Created
- Aug 31, 2026
- Last code push
- 7 days ago (Oct 6, 2026)
- Latest release
- No releases yet
- anthropic-api
- claude-code
- coding-agents
- free-gpu
- glm
- glm-5-3-flash
- jax
- kaggle
- llm-inference
- llm-serving
- long-context
- mixture-of-experts
- openai-api
- pallas
- qwen
- qwen3
- speculative-decoding
- tpu
- tpu-inference
- vllm
Similar rising repos
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151). Why it matters: helps you run models on your own hardware without an API bill.
- NVIDIA/skills+7est.
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG… Why it matters: relevant if AI is part of your coding workflow.
- syv-ai/HyperQwen+7est.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer… Why it matters: useful plumbing for shipping LLM-powered features.
- tt-a1i/archify+119est.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. Why it matters: relevant if AI is part of your coding workflow.
- herdrdev/herdr+56est.
the runtime your coding agents live on. Why it matters: relevant if AI is part of your coding workflow.
- devswha/herdr-web-ui+35est.
Browser and phone client for herdr: chat and live terminal for every agent pane, remote PCs over SSH, web push alerts. Why it matters: relevant if AI is part of your coding workflow.