Show HN: NightRun, bare metal LLM inference, no OS, boots from USB
A local LLM runtime that boots from USB and runs without a conventional operating system. Real boot, one cut: loading and prefill sped up, generation at actual speed (Llama 3.2 1B, QEMU/KVM, 8 cores). There is no Linux userspace hiding underneath.
- ▪A local LLM runtime that boots from USB and runs without a conventional operating system.
- ▪Real boot, one cut: loading and prefill sped up, generation at actual speed (Llama 3.2 1B, QEMU/KVM, 8 cores).
- ▪There is no Linux userspace hiding underneath.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,776 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/hardrave/NIGHTRUN |
| Publication time | Wed, 29 Jul 2026 14:36:24 +0000 |
| Retrieval time | 2026-07-29T14:48:09.784Z |
| Last seen | 2026-07-29T14:48:09.784Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | Zo8ty6pw2Xy8 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
A local LLM runtime that boots from USB and runs without a conventional operating system. Real boot, one cut: loading and prefill sped up, generation at actual speed (Llama 3.2 1B, QEMU/KVM, 8 cores). This is weird software. It boots straight into an LLM. There is no Linux userspace hiding underneath. Your machine's firmware starts NightRun directly, NightRun copies a quantized model into RAM, draws its own terminal on the framebuffer, and you chat. No kernel, no browser, no network stack, no host process. The machine does exactly one thing. Written in Rust. no_std where it counts. Runs on ordinary x86_64 PCs from a USB stick and on a Raspberry Pi 5 from an SD card. The 10-second version Run the installer. It builds a bootable image and flashes it to a USB stick or SD card.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.