DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to Run an 80B Qwen Model in 4.3GB of RAM: The Edge AI Revolution Explained
kaixintelligence profile

How to Run an 80B Qwen Model in 4.3GB of RAM: The Edge AI Revolution Explained

#ai #hardware #llm
Comments
6 min read
The AI Feature Is Cheap to Build and Expensive to Run
sagar_jain4010 profile

The AI Feature Is Cheap to Build and Expensive to Run

#ai #llm #costoptimization #engineering
Comments
3 min read
Why I Built a Local AI Assistant Instead of Yet Another Chatbot
_8c2bec12fe021319a0e1b profile
Jiwan

Why I Built a Local AI Assistant Instead of Yet Another Chatbot

#ai #llm #architecture #buildinpublic
Comments
5 min read
5 Coding Models You Can Actually Run on a Laptop in 2026
fernandonog profile

5 Coding Models You Can Actually Run on a Laptop in 2026

#ai #llm #qwen #bonsai
Comments
5 min read
DeepSeek V4 Is Now the 'Kill Line' of AI Models — Here's What That Means
xiaomodern profile

DeepSeek V4 Is Now the 'Kill Line' of AI Models — Here's What That Means

#deepseek #ai #llm #benchmark
Comments
3 min read
OpenAI divise par cinq le prix de Luna, pas ses coûts
thibault_monteiro profile

OpenAI divise par cinq le prix de Luna, pas ses coûts

#news #chatgpt #llm #openai
Comments
6 min read
The server rejected the norepinephrine — and that was the best thing that happened
jesuspantojap profile

The server rejected the norepinephrine — and that was the best thing that happened

#fhir #healthcare #llm #opensource
Comments
2 min read
Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 3: Giving the Agent Memory
ebrahim_arian_37097b72c7e profile

Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 3: Giving the Agent Memory

#ai #langchain #llm #tutorial
1
Comments 3
7 min read
Mnemara updated with the past couple of months of changes.
mekickdemonscreator profile

Mnemara updated with the past couple of months of changes.

#agents #ai #llm #software
1
Comments
2 min read
From "token" to "MoE": the LLM glossary in dependency order
mojalab profile

From "token" to "MoE": the LLM glossary in dependency order

#ai #llm #naturallanguageprocessing
Comments
17 min read
CoMem Explained — From Paper to Working Code in 10 Minutes
cofldus profile

CoMem Explained — From Paper to Working Code in 10 Minutes

#machinelearning #python #deeplearning #llm
Comments
6 min read
CLAUDE.md vs. a memory MCP: what actually goes where
wang1051992187 profile

CLAUDE.md vs. a memory MCP: what actually goes where

#agents #claude #llm #mcp
Comments 2
6 min read
Building low-latency semantic memory for coding agents with LanceDB
wang1051992187 profile

Building low-latency semantic memory for coding agents with LanceDB

#ai #database #llm #rag
Comments 1
9 min read
What Actually Happens During a Single LLM Call?
leo_c8398753453de189bcd profile

What Actually Happens During a Single LLM Call?

#ai #programming #llm #python
Comments
1 min read
The Promptfoo Acquisition Made Me Realize I Was Evaluating LLMs on Easy Mode
zoh007 profile
Zohair

The Promptfoo Acquisition Made Me Realize I Was Evaluating LLMs on Easy Mode

#llm #python #opensource #machinelearning
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.