DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Run DeepSeek-R1 on Your Laptop with Ollama

Run DeepSeek-R1 on Your Laptop with Ollama

473
Comments 19
10 min read
Streamlit in Snowflake App Catalog

Streamlit in Snowflake App Catalog

7
Comments
18 min read
Building Intelligent Multi-Agent Systems with CrewAI

Building Intelligent Multi-Agent Systems with CrewAI

5
Comments
5 min read
Run DeepSeek R-1 Thinking Model in Kaggle Notebook Using Ollama

Run DeepSeek R-1 Thinking Model in Kaggle Notebook Using Ollama

3
Comments
2 min read
Run DeepSeek Locally in Obsidian: Complete Beginner's Guide

Run DeepSeek Locally in Obsidian: Complete Beginner's Guide

23
Comments
3 min read
Mastering System Prompts for LLMs

Mastering System Prompts for LLMs

20
Comments
3 min read
Qwen2.5 Max Release Went Unnoticed in Deepseek Hysteria

Qwen2.5 Max Release Went Unnoticed in Deepseek Hysteria

11
Comments
6 min read
Building a Simple Powerful Chatbot Using ChromaDB and Sentence-Transformers

Building a Simple Powerful Chatbot Using ChromaDB and Sentence-Transformers

2
Comments
1 min read
General recommended VRAM Guidelines for LLMs

General recommended VRAM Guidelines for LLMs

14
Comments 2
3 min read
Oumi: Making AI Models Fully Open Source

Oumi: Making AI Models Fully Open Source

3
Comments 2
3 min read
GRPO Pitfalls Record

GRPO Pitfalls Record

1
Comments
2 min read
2024 - Ultimate guide to LLM analysis using NLP standalone

2024 - Ultimate guide to LLM analysis using NLP standalone

Comments
4 min read
Added cuda support for my custom neural architecture

Added cuda support for my custom neural architecture

Comments
1 min read
Deepseek R1 vs V3: Performance, Features, and Beyond

Deepseek R1 vs V3: Performance, Features, and Beyond

Comments
3 min read
Data Splitting: Breaking Down the Problem

Data Splitting: Breaking Down the Problem

Comments
3 min read
Why LLMs Fall Short: Why Large Language Models Aren't Ideal for AI Agent Applications

Why LLMs Fall Short: Why Large Language Models Aren't Ideal for AI Agent Applications

Comments
3 min read
GPT for Word. Use DeepSeek-R1 in Microsoft Word to Calculate Proportion of People with IQs Above 130.

GPT for Word. Use DeepSeek-R1 in Microsoft Word to Calculate Proportion of People with IQs Above 130.

10
Comments
1 min read
64 architecture for a neural network Architecture that thinks, adapts & creates

64 architecture for a neural network Architecture that thinks, adapts & creates

Comments
1 min read
LLMs in Prod'25: Real-World Insights from 2Tn+ Tokens

LLMs in Prod'25: Real-World Insights from 2Tn+ Tokens

1
Comments
2 min read
Quantum Computing and LLMs: Match Made in Heaven?

Quantum Computing and LLMs: Match Made in Heaven?

Comments
5 min read
Safeguarding Your Data When Using DeepSeek R1 In RAG Pipelines - Part II

Safeguarding Your Data When Using DeepSeek R1 In RAG Pipelines - Part II

1
Comments 1
6 min read
Découvrez Qwen-2.5-Max : Une Révolution dans le Domaine des Modèles Linguistiques

Découvrez Qwen-2.5-Max : Une Révolution dans le Domaine des Modèles Linguistiques

4
Comments
4 min read
Best Ways to Run LLM Locally on Mac

Best Ways to Run LLM Locally on Mac

102
Comments 5
4 min read
New implementation on watsonx.ai: automate RAG pipeline development & deployment with a SDK

New implementation on watsonx.ai: automate RAG pipeline development & deployment with a SDK

Comments
14 min read
AI-powered Corporate Jargon Translation with Amazon Bedrock

AI-powered Corporate Jargon Translation with Amazon Bedrock

2
Comments 1
3 min read
loading...