Hacker Blogs
Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #22741

A

aistack

Company blog · aistack.imec-int.com/blogaihardware

aistack is the company blog at aistack.imec-int.com, writing about ai and hardware. Since 2026, 3 different Hacker News readers have linked it 7 times, most often “Self-hosting Kimi K3: 20% more hardware cost, 20% better task resolution”. It is still writing: the last post was on 2026-10-08, and you can follow it by feed.

Visit the blog
7mentions?
3HN people?
2026–2026first – last linked?

Too few sampled comments (1) to say how often HN recommends it.?

Why HN links it

Linked as a record of Hacker News submissions about running the 2.78T-parameter Kimi K3 model locally on laptops, including a 29 GB RAM run at 0.50 tok/s. The comment is a list of bare links.

Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

We measure next-gen AI workloads on next-gen silicon. An imec initiative helping model, hardware, infrastructure and application builders shape their AI stack.

Most-linked posts?

  1. Self-hosting Kimi K3: 20% more hardware cost, 20% better task resolution
    2 people · 3 mentions · first linked 2026-07-23

What Hacker News says?

  1. 1vuio0pswjnm7 · 2026-08-01
    28 Jul 2026 21:35:19 UTC Running Kimi K3 on a M1 Max https://github.com/gavamedia/deltafin https://news.ycombinator.com/item?id=49090233 [ok] 29 Jul 2026 02:01:04 UTC Kimi K3 running on any device locally https://github.com/RightNow-AI/local-kimi https://news.ycombinator.com/item?id=49092591 [dead] 29 Jul 2026 13:49:32 UTC Show HN: Waste Run the full 2.78T-parameter Kimi K3 on a laptop https://news.ycombinator.com/i…

    Comment linking /blog/gpu-self-hosting

    on “Run Kimi K3 using 29 GB of RAM at 0.50 tok/s”
  2. flifenstein · 2026-09-15

    Submitted Harness your expectations: a 27B model matched GLM-5.3-Flash after leak fixes as a story · 3 points

    HN discussion
  3. flifenstein · 2026-07-29

    Submitted Self-hosting Kimi K3: 20% more hardware cost, 20% better task resolution as a story · 3 points

    HN discussion
  4. mindwraps · 2026-10-14

    Submitted Does quantization hurt coding agents? Deep-dive with actual numbers as a story · 2 points

    HN discussion
  5. mindwraps · 2026-09-18

    Submitted Fable 5.1 vs. Astra for coding: Fable 2X more expensive per task but solves more as a story · 2 points

    HN discussion
  6. mindwraps · 2026-09-10

    Submitted Benchmarking Claude Code, Codex and Pi on SWE-Bench Pro: Same Accuracy, 2x Cost as a story · 1 points

    HN discussion
  7. flifenstein · 2026-07-23

    Submitted How many devs can you fit on a GPU? as a story · 1 points

    HN discussion

Search all of HN for aistack.imec-int.com