thinkingcap-qwen3.8-27b-exl3-tandemllm
thinkingcap-qwen3.8-27b-exl3-tandemllm is ThinkingCap Kearuga EXL3: TandemLLM-first DGX Spark serving, independent RTX 5090 receipts and a retained TensorFold reproduction recipe. - 0xWhiteMage/thinkingcap-qwen3.8-27b-exl3-tandemllm. It is ranked #2341 on the Dev Radar, in Hosting & infra, first seen 11 days ago and shared in 2 posts (2.8k views).
GitHub - 0xWhiteMage/thinkingcap-qwen3.8-27b-exl3-tandemllm: ThinkingCap Kearuga EXL3: TandemLLM-first DGX Spark serving, independent RTX 5090 receipts and a retained TensorFold reproduction recipe. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings 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 {{ message }} Repository navigation thinkingcap-qwen3.8-27b-exl3-tandemllm Public…
What people said about thinkingcap-qwen3.8-27b-exl3-tandemllm on X
Huge shoutout to @niklaslenz_ai for adding his independent RTX 5090 and DGX Spark receipts with @0xBakeer's TandemLLM! 🔥 I've updated the recipe to serve the Qwen3.8 27B Kearuga (ThinkingCap) on TandemLLM natively with avg. of 62.22 tok/s! Recipe below:…
— @0xWhiteMage, 11 days ago · 16 likes · see the post
Imagine quantising weights to 4-bits (from BF16) and still getting 97.79% top-1 agreement. This is the Kearuga way. Any requests for current or upcoming models I should apply the Kearuga quantisation on? 😋
— @0xWhiteMage, 8 days ago · 13 likes · see the post
Alternatives to thinkingcap-qwen3.8-27b-exl3-tandemllm
- boat by ASCII — omfg @theo just released a video that talks about
- Cloudflare Docs — Deploy it to Cloudflare
- Cloudflare Blog — Cloudflare has patched the issue
- Railway — Connect Neon
- Giotto OS — Use Giotto
- Boundless — Apply for access
thinkingcap-qwen3.8-27b-exl3-tandemllm in numbers
- Rank on the Dev Radar: #2341 of 8798
- Shared in 2 posts by 1 account: @0xWhiteMage
- 2.8k views on those posts
- First seen 11 days ago, last shared 8 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Hosting & infra
FAQ
What is thinkingcap-qwen3.8-27b-exl3-tandemllm?
ThinkingCap Kearuga EXL3: TandemLLM-first DGX Spark serving, independent RTX 5090 receipts and a retained TensorFold reproduction recipe. - 0xWhiteMage/thinkingcap-qwen3.8-27b-exl3-tandemllm It was first shared on X 11 days ago and is ranked #2341 on the Dev Radar.
Is thinkingcap-qwen3.8-27b-exl3-tandemllm free?
It is open source.
Who shared thinkingcap-qwen3.8-27b-exl3-tandemllm?
1 account on X, including @0xWhiteMage, in 2 posts totalling 2.8k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.