Skip to main content
Scour
Discover
Docs
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Open Source AI
🔓 Open Source AI
Llama, Mistral, open weights, Hugging Face, open models
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
819
posts in
44.0
ms
🤖
AI
pyimagesearch.com
·
20h
20 hours ago
Google DeepMind’s
Gemma
4: MoE, Efficiency Tricks, and Benchmarks
Covers
7 stories
See all stories this covers
including
GitHub here . You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inferen...
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Google DeepMind’s Gemma 4: MoE, Efficiency Tricks, and Benchmarks
🤖
AI
fitservers.com
·
3d
3 days ago
The Complete Guide to Deploying DeepSeek R1 on a Dedicated Server
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The Complete Guide to Deploying DeepSeek R1 on a Dedicated Server
🆕
New AI
ByteByteGo Newsletter
·
2d
2 days ago
EP219: 12
Open-source
LLMs
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for EP219: 12 Open-source LLMs
🆕
New AI
Simon Willison’s Weblog
·
5d
5 days ago
GLM-5.2 is probably the most powerful text-only
open
weights
LLM
Covers
3 stories
See all stories this covers
including
zai-org/GLM-5.2 is here!
Covered by
5 sources
See all sources covering this story
including
vettedconsumer.com
,
notes.dsebastien.net
Discussed on
Hacker News
and
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for GLM-5.2 is probably the most powerful text-only open weights LLM
🤖
AI
Posts by Year
·
23h
23 hours ago
Mac Studio: The Best Local
LLM
Workstation Money Can(‘t) Buy
Covers
7 stories
See all stories this covers
including
Introducing Claude Opus 4.8
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Mac Studio: The Best Local LLM Workstation Money Can(‘t) Buy
🆕
New AI
arXiv
·
4h
4 hours ago
Evaluating LLMs for Real-World Web Vulnerability Detection
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Evaluating LLMs for Real-World Web Vulnerability Detection
🤖
AI
Hacker News
·
1d
1 day ago
Good results
fine
tuning
a local
LLM
like Qwen 3:0.6B to categorize questions
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions
🤖
AI
GitHub
·
15h
15 hours ago
Show HN: Loqi, a "local-first" translation tool using
Ollama/llama.cpp
Covers
Ollama
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Show HN: Loqi, a "local-first" translation tool using Ollama/llama.cpp
📋
MCP
medium.com
·
1d
1 day ago
Debugging Deployments with
Gemma
12B, TPU v6e-1, MCP, and Antigravity CLI
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Debugging Deployments with Gemma 12B, TPU v6e-1, MCP, and Antigravity CLI
🤖
AI
llama-dash.dev
·
21h
21 hours ago
One go-to control plane for local inference
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for One go-to control plane for local inference
🆕
New AI
youtube.com
Content type:
Video
·
6d
6 days ago
Twelve
models
worth knowing in 2026, each with one standout strength. 1.
Llama
4 Scout: Meta's first natively multimodal
open-weight
model. 2. DeepSeek V4: A Mi...
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Twelve models worth knowing in 2026, each with one standout strength. 1. Llama 4 Scout: Meta's first natively multimodal open-weight model. 2. DeepSeek V4: A Mi...
🆕
New AI
datalab.to
·
2d
2 days ago
Introducing lift:
open-weights
structured extraction
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Introducing lift: open-weights structured extraction
🤖
AI
XDA
·
18h
18 hours ago
I used Meta
Llama
4,
Qwen
3-Coder and
Gemma
4 to develop a python app, and only one model is worth keeping for developers
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for I used Meta Llama 4, Qwen 3-Coder and Gemma 4 to develop a python app, and only one model is worth keeping for developers
🆕
New AI
notes.dsebastien.net
·
2d
2 days ago
Mellum2
Covers
Mellum2 Goes Open Source: A Fast Model for AI Workflows
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Mellum2
🆕
New AI
yaroslavvb.github.io
·
4d
4 days ago
How far behind is
open-source
AI
?
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for How far behind is open-source AI?
🤖
AI
GitHub
·
2h
2 hours ago
Show HN: MinLlama –
Llama
3.2 inference in ~100 lines of NumPy
Covers
uv
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy
🤖
AI
Fortune
·
1d
1 day ago
NBC’s Tom
Llamas
climbed from 15-year-old intern to the top anchor chair—and still isn’t satisfied: ‘If you’re not growing, you’re dying’
Covered by
Poynter
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for NBC’s Tom Llamas climbed from 15-year-old intern to the top anchor chair—and still isn’t satisfied: ‘If you’re not growing, you’re dying’
💾
Prompt Caching
Anyscale blog posts
·
4d
4 days ago
High Performance Distributed Inference with Ray Serve
LLM
Covered by
Google Cloud Blog
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for High Performance Distributed Inference with Ray Serve LLM
🤖
AI
ubuntu.com
·
1d
1 day ago
Developing web apps with local
LLM
inference
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Developing web apps with local LLM inference
🤖
AI
arXiv
·
4h
4 hours ago
Post-Training Recipe, More Than
Model
Family, Shapes Multi-Agent
LLM
Conversational Behavior
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report