TOtosh·Apr 30, 2023Submission
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
1 points · Open discussionkuleshov
minillm
Python2023–2023
kuleshov / minillm
minillm
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
3Distinct people
5Mentions
0Explicit recommenders
978GitHub stars
What to know before exploring
What it is
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
GitHub
Where it is used
No documented product use has been verified yet.
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
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM 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 week5 dated mentions
Observed mentions: 2023-03-16 23:38:20 UTC to 2023-04-30 18:17:43 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Mar 13 | 2023-03-13 00:00:00 UTC | 2023-03-20 00:00:00 UTC | 4 | 1 | 3 |
| Mar 20 | 2023-03-20 00:00:00 UTC | 2023-03-27 00:00:00 UTC | 0 | 0 | 0 |
| Mar 27 | 2023-03-27 00:00:00 UTC | 2023-04-03 00:00:00 UTC | 0 | 0 | 0 |
| Apr 3 | 2023-04-03 00:00:00 UTC | 2023-04-10 00:00:00 UTC | 0 | 0 | 0 |
| Apr 10 | 2023-04-10 00:00:00 UTC | 2023-04-17 00:00:00 UTC | 0 | 0 | 0 |
| Apr 17 | 2023-04-17 00:00:00 UTC | 2023-04-24 00:00:00 UTC | 0 | 0 | 0 |
| Apr 24 | 2023-04-24 00:00:00 UTC | 2023-05-01 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
5 sourcesDon't have a $5k MacBook to run LLAMA65B? MiniLLM runs LLMs on GPUs in <500 LOC
3 points · Open discussionThere are also equally easy to use open source systems, check out this one for example: https://github.com/kuleshov/minillm
In TextSynth ServerTry this: it installs with a simple python command if you have an NVIDIA GPU: https://github.com/kuleshov/minillm
In Load LLaMA Models InstantlyGitHub link: https://github.com/kuleshov/minillm
In MiniLLM: A minimal system for running LLMs on consumer-grade Nvidia GPUs