AI

Feeds to Scour
SubscribedAll
Scoured 275 posts in 5.3 ms

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM

 🐧unix

Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA

 🕸️graphs
everylocalai.com··DEV

DiffusionGemma 26B A4B results on my 5090

 🐧unix

Orchestrate your LLM pipeline. Locally

 🐧unix
llmforge.app··Hacker News

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

 🧱data structures  Content type: Blog
bric.pe.kr··DEV

A Complete Beginner's Guide to Local LLM Inference

 🧩lisp  Content type: Blog
khnsakhnm.medium.com·

local llm on laptop 780M GPU using llama + gemma 4 qat

 🐧unix  Content type: Blog
alper.bearblog.dev·

What Ollama Reveals About Local AI, Agents, and Open Models

 🕸️graphs  Content type: Blog
odsc.medium.com·

147th airhacks tv: Local LLMs, LightMetal, ZSmith Agents, AI Rails, Saving Tokens

 🐧unix  Content type: Blog
adambien.blog·

6. Air-Gapped Claude Code - The Claude Code SRE Handbook

 🧱data structures

Ask HN: Any Local LLM can I run without GPU for Local Agentic workflow AI?

 🧱data structures  Content type: Discussion

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.

 🧱data structures  Content type: Code
github.com··DEV

Improved performance and model support with GGUF

 🕸️graphs  Content type: Blog
ollama.com·

Two old GPUs I salvaged are doing more AI work than a brand new $2000 card, and I won't be upgrading anytime soon

 🧱data structures
xda-developers.com·

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

 🧱data structures  Content type: Academic
arxiv.org·

Token4Token — pay-per-token inference on Gnosis + Swarm

 🧱data structures
t4t.eth.link··Hacker News

Unsloth Gemma 4 QAT

 🧱data structures
unsloth.ai·

On-device AI is a margin decision

 🧱data structures  Content type: Blog
ziraph.com··Hacker News

Fixing a stuck Ollama runner and building a GPU watchdog

 🐧unix

There's one AI machine that doesn't need a nuclear power station to run, and it points to a potential way forward in the memory crisis

 🧱data structures  Content type: News
pcgamer.com
·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help