Nicheloom visits: 60,536 all-time · 7,913 in the last 7 days

The opportunity tracker for new startups.

Today: 895 launches · Niche of the day: browser-based video games · See what launched today →

yasakani

Local LLM engine for Windows and one NVIDIA RTX 5090, built for Qwen3.8-27B

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

GITHUB · launched Nov 12, 2026 · 103 upvotes (top 33%) · 0 views

Niche: llm inference engines · 134 launches, 3 in the last 7 days ▼ -40% · Explore this niche →

Category and tags

  • Horizontal
  • Model & infra
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

Could you build this?

Partial A Windows wrapper around existing local inference runtimes is vibe-codeable, but a performant engine tuned for one GPU and a specific large model needs low-level CUDA and quantization work beyond vibe coding.

What it would actually take: A basic version can wrap llama.cpp or vLLM with a UI and API server. Competitive performance on an RTX 5090 requires custom CUDA kernels, quantization such as GGUF or AWQ tuning, KV-cache and memory management, and access to the model weights. That calls for ML systems and GPU performance engineers.

Competitors

Other products that read as similar to this one : 2654 launches clear the similarity bar, closest 8 shown.

Attention rank: #912 of 2655 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 375 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.