HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
JustVugg
colibri
C2026–2026
JustVugg / colibri

colibri

A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.

16Distinct people
18Mentions
0Explicit recommenders
50.3KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 8:59:02 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week18 dated mentions

Observed mentions: 2026-07-09 08:05:04 UTC to 2026-09-21 11:20:45 UTC. Weeks start Monday, UTC.

02462026-07-06 00:00:00 UTC to 2026-07-13 00:00:00 UTC (exclusive): 3 mentions; 1 submissions, 2 commentsJul 62026-07-13 00:00:00 UTC to 2026-07-20 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-07-20 00:00:00 UTC to 2026-07-27 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-07-27 00:00:00 UTC to 2026-08-03 00:00:00 UTC (exclusive): 6 mentions; 0 submissions, 6 comments2026-08-03 00:00:00 UTC to 2026-08-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-08-10 00:00:00 UTC to 2026-08-17 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 commentsAug 102026-08-17 00:00:00 UTC to 2026-08-24 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-08-24 00:00:00 UTC to 2026-08-31 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-08-31 00:00:00 UTC to 2026-09-07 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-09-07 00:00:00 UTC to 2026-09-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-14 00:00:00 UTC to 2026-09-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-21 00:00:00 UTC to 2026-09-28 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsSep 21

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Jul 62026-07-06 00:00:00 UTC2026-07-13 00:00:00 UTC312
Jul 132026-07-13 00:00:00 UTC2026-07-20 00:00:00 UTC101
Jul 202026-07-20 00:00:00 UTC2026-07-27 00:00:00 UTC202
Jul 272026-07-27 00:00:00 UTC2026-08-03 00:00:00 UTC606
Aug 32026-08-03 00:00:00 UTC2026-08-10 00:00:00 UTC000
Aug 102026-08-10 00:00:00 UTC2026-08-17 00:00:00 UTC211
Aug 172026-08-17 00:00:00 UTC2026-08-24 00:00:00 UTC101
Aug 242026-08-24 00:00:00 UTC2026-08-31 00:00:00 UTC101
Aug 312026-08-31 00:00:00 UTC2026-09-07 00:00:00 UTC101
Sep 72026-09-07 00:00:00 UTC2026-09-14 00:00:00 UTC000
Sep 142026-09-14 00:00:00 UTC2026-09-21 00:00:00 UTC000
Sep 212026-09-21 00:00:00 UTC2026-09-28 00:00:00 UTC110

What Hacker News says

3 sources
vforno·Jul 9, 2026Submission

Show HN: Getting GLM 5.2 running on my slow computer

A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context. How it responds in int4 and whether the quality is maintained or not. Until I got to the point, on my computer with 32GB of RAM, I was able to communicate with GLM 5.2 with times that, of course, aren't high in cold start, but even then, we're talking
Read the rest
about 0.1 tok/s, but that wasn't important to me. The important thing was the journey to reach this goal. I just wanted it to work at all costs, even slowly. So I created Colibrì, which was born from a very simple idea, to be honest, but tested in every way, where a 744B Mixture-of-Experts model activates only ~40B parameters per token—and only ~11 GB of those change from token to token (the routed experts). So: The dense part (attention, shared experts, embeddings—~17B params) stays resident in RAM at int4 (~9.9 GB); The 21,504 routed experts (75 MoE layers × 256 experts + the MTP head, ~19 MB each at int4) live on disk (~370 GB) and are streamed on demand, with a per-layer LRU cache, an optional pinned hot-store, and the OS page cache as a free L2. The engine is a single C file (c/glm.c, ~1,300 lines) plus small headers. No BLAS, no Python at runtime, no GPU.No GPU or serious hardware because I don't have that hardware so I can't test it on hardware that is more powerful than my computer.Colibrì is a one-person project, written and tested entirely on a 12-core laptop with 25 GB of RAM — the numbers above are the ceiling of what I can measure at home. Any feedback is welcome! (and if anyone wanted to participate in the project I would be delighted) Repo: https://github.com/JustVugg/colibri
937 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.