Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Open Source LLMs
🔓 Open Source LLMs
Specific
open source LLM, Llama, Mistral, Ollama, local models
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
233
posts in
5.3
ms
Gemma
4 QAT
models
: Optimizing model compression for mobile and laptop efficiency
🧠
LLMs
Content type:
News
Content type:
Blog
blog.google
·
5d
5 days ago
·
Hacker News
Actions for Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
Doubling
Qwen3.6-27B
on One RTX 3090:
ollama
llama.cpp
+ MTP, Lever by Lever (35.7 80.2 tok/s)
🛠️
AI Tooling
Content type:
Blog
dev.to
·
1d
1 day ago
·
DEV
Actions for Doubling Qwen3.6-27B on One RTX 3090: ollama llama.cpp + MTP, Lever by Lever (35.7 80.2 tok/s)
Neo-X7/Neo-AI: A fully offline AI assistant powered by
Ollama
. Stores and retrieves conversations using SQLite + LanceDB vector search. No cloud. No API keys. Runs entirely on your machine.
🛠️
AI Tooling
Content type:
Code
github.com
·
6h
6 hours ago
·
DEV
Actions for Neo-X7/Neo-AI: A fully offline AI assistant powered by Ollama. Stores and retrieves conversations using SQLite + LanceDB vector search. No cloud. No API keys. Runs entirely on your machine.
Integrate on-device AI
models
into your app using Core AI - WWDC26 - Videos
💡
AI
developer.apple.com
·
2d
2 days ago
·
Hacker News
Actions for Integrate on-device AI models into your app using Core AI - WWDC26 - Videos
DiffusionGemma: The Developer Guide
💡
AI
Content type:
Blog
developers.googleblog.com
·
19h
19 hours ago
Actions for DiffusionGemma: The Developer Guide
Ask HN: Is it feasible to run a
model
on device for complete privacy?
🧠
LLMs
Content type:
Discussion
news.ycombinator.com
·
3d
3 days ago
·
Hacker News
Actions for Ask HN: Is it feasible to run a model on device for complete privacy?
Token4Token — pay-per-token inference on Gnosis + Swarm
🛠️
AI Tooling
t4t.eth.link
·
1d
1 day ago
·
Hacker News
Actions for Token4Token — pay-per-token inference on Gnosis + Swarm
Less-relevant results
On-device AI is a margin decision
🛠️
AI Tooling
Content type:
Blog
ziraph.com
·
1h
1 hour ago
·
Hacker News
Actions for On-device AI is a margin decision
Show HN: Audit any AI/data pairing with Veritrooper
🧠
LLMs
veritrooper.com
·
5d
5 days ago
·
Hacker News
Actions for Show HN: Audit any AI/data pairing with Veritrooper
Node.js Annual Releases, Terraform 1.15,
Gemma
4 Multimodal
✨
Vibe Coding
Content type:
Discussion
thedevsignal.com
·
1d
1 day ago
·
DEV
Actions for Node.js Annual Releases, Terraform 1.15, Gemma 4 Multimodal
No Cloud, No Cost: Build an Offline Visual AI Agent with
Gemma
4
🛠️
AI Tooling
Content type:
Blog
dev.to
·
16h
16 hours ago
·
DEV
Actions for No Cloud, No Cost: Build an Offline Visual AI Agent with Gemma 4
Job Searcher
💡
AI
Content type:
Blog
huggingface.co
·
4d
4 days ago
Actions for Job Searcher
Claude Now Writes 80% of Its Own Code — Anthropic's Self-Improvement Milestone Arrives Faster Than Expected
🔶
Claude
the-agent-report.com
·
1d
1 day ago
·
DEV
Actions for Claude Now Writes 80% of Its Own Code — Anthropic's Self-Improvement Milestone Arrives Faster Than Expected
Large companies can add a
local
LLM
filter layer to considerably reducing their AI costs
🧠
LLMs
umrashrf.github.io
·
4d
4 days ago
·
Hacker News
Actions for Large companies can add a local LLM filter layer to considerably reducing their AI costs
local
AI agents for Cursor with pre-tuned marketplace/commu
🛠️
AI Tooling
locaible.com
·
6h
6 hours ago
·
Hacker News
Actions for local AI agents for Cursor with pre-tuned marketplace/commu
How I benchmarked a 100%
local
RAG pipeline to 9/9 (zero API keys)
📚
RAG
buy.polar.sh
·
2d
2 days ago
·
DEV
Actions for How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)
ComfyUI NVFP4 in 2026: 3 Faster Image Generation on RTX 50-Series (and the Right Format for RTX 40-Series)
💡
AI
Content type:
Blog
dev.to
·
12h
12 hours ago
·
DEV
Actions for ComfyUI NVFP4 in 2026: 3 Faster Image Generation on RTX 50-Series (and the Right Format for RTX 40-Series)
martidu4/honey-ai: 🍯 All-in-one AI honeypot powered by
local
LLMs
. SSH, HTTP, FTP, Telnet, SMTP, MySQL, Redis, Git, VNC, RDP — with canary tokens, tarpits, GZIP bombs, and threat intel reporting.
🛠️
AI Tooling
Content type:
Code
github.com
·
4h
4 hours ago
·
Hacker News
Actions for martidu4/honey-ai: 🍯 All-in-one AI honeypot powered by local LLMs. SSH, HTTP, FTP, Telnet, SMTP, MySQL, Redis, Git, VNC, RDP — with canary tokens, tarpits, GZIP bombs, and threat intel reporting.
I Could Solve the Problem, but I Could Not Explain It in English. That Is How ExtraBrain Started
🔶
Claude
extrabrain.app
·
3d
3 days ago
·
DEV
Actions for I Could Solve the Problem, but I Could Not Explain It in English. That Is How ExtraBrain Started
Purpose-built
local
AI agents
✍️
Prompt Engineering
Content type:
Blog
samihonkonen.com
·
1d
1 day ago
·
Hacker News
Actions for Purpose-built local AI agents
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
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
Browse
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