HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
jankais3r
LLaMA_MPS
Python2023–2023
jankais3r / LLaMA_MPS · Archived

LLaMA_MPS

Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon GPUs.

AI & Machine LearningMobile & DesktopCommunication & Social
Explore on GitHubRead Hacker News discussions
2Distinct people
2Mentions
0Explicit recommenders
575GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon 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 day2 dated mentions

Observed mentions: 2023-04-12 21:32:58 UTC to 2023-04-29 22:35:07 UTC.

012023-04-12 00:00:00 UTC to 2023-04-13 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsApr 122023-04-13 00:00:00 UTC to 2023-04-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-14 00:00:00 UTC to 2023-04-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-15 00:00:00 UTC to 2023-04-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-16 00:00:00 UTC to 2023-04-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-17 00:00:00 UTC to 2023-04-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-18 00:00:00 UTC to 2023-04-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-19 00:00:00 UTC to 2023-04-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-20 00:00:00 UTC to 2023-04-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsApr 202023-04-21 00:00:00 UTC to 2023-04-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-22 00:00:00 UTC to 2023-04-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-23 00:00:00 UTC to 2023-04-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-24 00:00:00 UTC to 2023-04-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-25 00:00:00 UTC to 2023-04-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-26 00:00:00 UTC to 2023-04-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-27 00:00:00 UTC to 2023-04-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-28 00:00:00 UTC to 2023-04-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-29 00:00:00 UTC to 2023-04-30 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsApr 29

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
Apr 122023-04-12 00:00:00 UTC2023-04-13 00:00:00 UTC101
Apr 132023-04-13 00:00:00 UTC2023-04-14 00:00:00 UTC000
Apr 142023-04-14 00:00:00 UTC2023-04-15 00:00:00 UTC000
Apr 152023-04-15 00:00:00 UTC2023-04-16 00:00:00 UTC000
Apr 162023-04-16 00:00:00 UTC2023-04-17 00:00:00 UTC000
Apr 172023-04-17 00:00:00 UTC2023-04-18 00:00:00 UTC000
Apr 182023-04-18 00:00:00 UTC2023-04-19 00:00:00 UTC000
Apr 192023-04-19 00:00:00 UTC2023-04-20 00:00:00 UTC000
Apr 202023-04-20 00:00:00 UTC2023-04-21 00:00:00 UTC000
Apr 212023-04-21 00:00:00 UTC2023-04-22 00:00:00 UTC000
Apr 222023-04-22 00:00:00 UTC2023-04-23 00:00:00 UTC000
Apr 232023-04-23 00:00:00 UTC2023-04-24 00:00:00 UTC000
Apr 242023-04-24 00:00:00 UTC2023-04-25 00:00:00 UTC000
Apr 252023-04-25 00:00:00 UTC2023-04-26 00:00:00 UTC000
Apr 262023-04-26 00:00:00 UTC2023-04-27 00:00:00 UTC000
Apr 272023-04-27 00:00:00 UTC2023-04-28 00:00:00 UTC000
Apr 282023-04-28 00:00:00 UTC2023-04-29 00:00:00 UTC000
Apr 292023-04-29 00:00:00 UTC2023-04-30 00:00:00 UTC101

What Hacker News says

2 sources
anentropic·Apr 12, 2023
I saw this: https://github.com/jankais3r/LLaMA_MPS it runs slightly slower on the GPU than under llama.cpp but uses much less power doing so I would guess the slowness is due to immaturity of the PyTorch MPS backend, the asitop graphs show it doing a bunch of cpu along with the gpu, so it might be inefficiently falling back to cpu for some ops and swapping layers back and forth (I have no idea, just guessing)
In Databricks Releases 15K Record Training Corpus for Instruction Tuning LLMs

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.