- This event has passed.
Large Language Model (LLMs) on Edge Devices
February 23, 2025 @ 2:30 pm - 4:30 pm
Completed Event
Event Details
Description
We are thrilled to invite you to an engaging two-hour session focused on running ML Models and Large Language Models – (LLMs) on edge devices under low-resource settings.
This event will delve into methods and techniques such as pruning, quantisation, compression, and distillation to optimize performance on devices like the Raspberry Pi, Jetson Nano, and CPU-only setups. Participants will gain hands-on experience with leading software tools and frameworks, including HuggingFace, Ollama, vLLMs, llama.cpp, and lmstudio. Join us for this insightful session to explore the cutting-edge of edge computing and enhance your skills in deploying efficient models in constrained environments. We look forward to seeing you there! 2hrs – talk time
Date & Time
📅 Date: February 23rd 2025 (Sunday)
⏰ Time: 2:30 PM – 4:30 PM
Location
OJone Building, 72, Service Rd, LRDE Layout, Doddanekundi, Bengaluru,
Karnataka 560037, India
Speakers
Technical Focus
Methods & Techniques
✅ Pruning
✅ Quantization
✅ Compression
✅ Distillation
Target Devices
👉 Raspberry Pi
👉 Jetson Nano
👉 CPU-only systems
Software Tools & Frameworks
🛠 Hugging Face
🛠 Ollama
🛠 vLLMs
🛠 llama.cpp
🛠 lmstudio
Gallery
