🚀 Medial Secures Investment on Shark Tank India - Fueling the Future of Professional Social Networking. 🔥

News

Messages

Try our Valuation Calculator →

Back

Haran Naresh K
•

Medial • 5m

🚀 Running Deepseek R1 1.5B on Ollama – AI at My Fingertips! 🤖🔥 Just set up and tested the Deepseek R1 1.5B model using Ollama, and I’m impressed with how seamless the experience is! This model is an efficient and capable LLM, and running it locally means privacy, control, and customization without relying on cloud-based APIs. 💡 Why does this matter? Edge AI is the future—powerful models running locally enhance performance and privacy. Experimentation with different models allows for more tailored AI experiences. Open-source AI solutions give us more freedom to explore and innovate! I asked it about the Seven Wonders of the World, and it started reasoning like a human, making connections, and even questioning historical interpretations! 🤯 The AI space is evolving fast, and tools like Ollama make it easier than ever to deploy models on our machines. Excited to push its limits and explore more applications! Are you experimenting with local LLMs? Let’s discuss! 🚀

4 Replies

Replies (4)

Ajink Gupta

🥴 • 5m

we are distilling for android

1 Reply

Anonymous 1

Hey I am on Medial • 5m

if you’re pushing limits, have you tried stacking it with other models or integrating it into a custom app? Curious to know how far you can take it

Recommendations from Medial

Nakul Pant

Looking for exciting... • 5m

Deepseek on local - Deepseek if running over ollama states it is running over Deepseek servers !!

Haran Naresh K
•

Medial • 5m

Try the new Deepseek R1 with the Deepseek AI App

9 Replies

Rohit joshi

Dev dev dev • 4m

🚀 New Video Alert! 🎉 We've just released a tutorial on building a Retrieval-Augmented Generation (RAG) application using Ollama and Microsoft's Phi-3 model. Key Points: Ollama:A platform that enables running large language models locally, enhanc

Chamarti Sreekar

Passionate about Pos... • 1m

Apple just exposed the truth behind so-called AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini: They’re not actually reasoning — they’re just really good at memorizing patterns. Here’s what Apple found:

Nawal

Entrepreneur | Build... • 5m

Perplexity CEO ready to invest $1m into Indians who can develop SOTA foundation models and $10m more if it can beat DeepSeek R1 benchmarks.

4 Replies

Pulakit Bararia

Building Snippetz la... • 4m

AI shouldn’t be a luxury—it should run anywhere, even on low-powered devices, without costly hardware or cloud dependency. Companies like TinyML, Edge Impulse, LM Studio, Mistral AI, Llama (Meta), and Ollama are already making AI lighter, faster, a

3 Replies

Chamarti Sreekar

Passionate about Pos... • 5m

Now might be the perfect opportunity for Rabbit to take a moonshot. Imagine, if you will, Rabbit R1 powered by DeepSeek R1. 🤯

3 Replies

Karthikeya Kollu

building @Orian(Olla... • 12m

Mathstral is doing a pretty good job! Here are the results, and I'll be testing all its capabilities. If you're curious about the extension I'm using check it out here: https://chromewebstore.google.com/detail/orian-ollama-webui/omjofoiomojnencdajlji

Sarthak Gupta

Developer • 2m

Big news! AnyLLM just got even better with 30+ new LLMs. 🎉 We've added some really exciting ones like Gemini 2.0 Flash, DeepSeek R1, and Compound models. Can't wait for you all to check them out! Visit now at anyllm.xyz and experience the best model

Divyam Gupta

Building products, l... • 1m

Google Unveils AI Edge Gallery: On-Device Generative AI Without Internet Google has launched the AI Edge Gallery, an experimental app that brings cutting-edge Generative AI models directly to your Android device. Once a model is downloaded, all proc