LocalLLaMA

Hot Top New Active

List Tile Wide tile

Beginner questions thread

by noneabove1182

2

Free Open-Source AI LLM Guide

by Blaed

0

Best Upgrade Path for my Desktop

5

I'm I the only one blown away by AI?

by

Mozilla's Llamafile 0.8.2 Scores Big With New AVX2 Performance Optimizations

by ylai

0

Llama 3 Establishes Meta as the Leader in “Open” AI

by ylai

2

Localllama setup for $100k.

by Timely_Jellyfish_2077

Eric Hartford on X: "I am super excited to announce that I've accepted a position with @TensorWaveCloud - focused on training AI models with @AMDInstinct technologies!"

by

0

Meta's Llama 3 will force OpenAI and other AI giants to up their game

by ylai

Meta releases Llama 3, claims it's among the best open models available

by veer66

2

New Mistral model is out

by The Hobbyist

7

Meta confirms that its Llama 3 open source LLM is coming in the next month

by ylai

4

LLaMA Now Goes Faster on CPUs

by ylai

1

What's the current recommendation for an anime oriented model?

by

0

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to ach

by

0

Dock GPU to Laptop or to small SOC?

by

5

Dock GPU to Laptop or to small SOC?

by

2

AnythingLLM | The ultimate AI business intelligence tool

by

9

Open web UI - a web UI primarily for ollama that has a bunch of useful functionally

by

1

Evolving New Foundation Models: Unleashing the Power of Automating Model Development

by ylai

0

GaLore: Advancing Large Model Training on Consumer-grade Hardware

by ylai

0

Mistral 7B v0.2 Base (released at SHACK15sf hackathon)

by ylai

0

Ollama now supports AMD graphics cards

by turkishdelight

0

T-Ragx - Enhancing Translation with RAG-Powered LLMs

by rayliuca

0

My personal collection of interesting models I've quantized from the past week (yes, just week)

by noneabove1182

0

[Paper] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

by rufus

0

Gemma 2B vs Phi-2

by acec

0

NVIDIA Chat With RTX

by

0

Meet ‘Smaug-72B’: The new king of open-source AI

by ylai

0

itsme2417/PolyMind: A multimodal, function calling powered LLM webui.

by noneabove1182

0

Introducing Nomic Embed: A Truly Open Embedding Model

by noneabove1182

0

Uncensored Mixtral 8x7B with 4 GB of VRAM

by glibg10b

0

Mistral CEO confirms ‘leak’ of new open source AI model nearing GPT-4 performance

by ylai

0

Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development

by ylai

0

A question about running LLMs with an AMD card

by

0

Noob here, what's the best overall model for getting started with ?

by

0

Zuckerberg wants to build artificial general intelligence with 350K Nvidia H100 GPUs

by ylai

0

InternLM2 models llama-fied

by noneabove1182

0

Building a fully local LLM voice assistant to control my smart home

by

exu

0

argilla released distilabeled-Hermes-2.5-Mistral-7B

by Reddy

0

Mixtral of Experts

by ylai

0

WizardLM/WizardCoder-33B-V1.1 released!

by noneabove1182

0

Microsoft announces WaveCoder

by noneabove1182

0

How to make LLMs go fast

by Alex

0

GitHub - SJTU-IPADS/PowerInfer: High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

by ylai

0

2023, year of open LLMs

by ylai

0

A Systems Programmer's Perspectives on Generative AI

by Alex

0

Training a model without a GPU

by

0

Looking for a low-end setup

by

Rez

0

Mistral shocks AI community as latest open source model eclipses GPT-3.5 performance

by ylai

0

Mixture of Experts Explained (Huggingface blog)

by noneabove1182

0

Mistral releases version 0.2 of their 7B model

by noneabove1182

0

QuIP#: SOTA 2 bit LLMs

0

ByteDance AI Promises Stronger than Gemini Open Weight GPT Dropping Soon

by ylai

0

Mistral drops a new magnet download

by noneabove1182

0

Inside the A.I. Arms Race That Changed Silicon Valley Forever

by ylai

0

LLMs made into single-file executables with llamafile

by

0

Unsloth: 80% faster 50% less memory LLM finetuning

0

I'm having a fantastic time with this model.

by undermine

0

Orca 2: Teaching Small Language Models How to Reason

by noneabove1182

0

Hundreds of OpenAI employees threaten to resign and join Microsoft

by noneabove1182

0

Catch me if you can! How to beat GPT-4 with a 13B model | LMSYS Org

by noneabove1182

0

TensorRT-LLM evaluation of the new H200 GPU achieves 11,819 tokens/s on Llama2-13B

by noneabove1182

0

...

by CoderSupreme

0

ExUI - a lightweight web UI for ExLlamaV2 by turboderp

by noneabove1182

0

...

by CoderSupreme

0