Quantized Llama models with increased speed and a reduced memory footprint (ai.meta.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of ai.meta.com: Quantized Llama models with increased speed and a reduced memory footprint

First screen, captured 2 years ago.

Looks similar

Screenshot of ai.meta.com: Llama 3.2: Revolutionizing edge AI and vision with open, customizable models

Llama 3.2: Revolutionizing edge AI and vision with open, customizable models (ai.meta.com)

861 points by nmwnmw 2 years ago | 298 comments

Meta AI blog post announcing Llama 3.2, including vision-capable models and lightweight models for edge and mobile devices.

llama meta large-language-models vision-models

Screenshot of ai.meta.com: Update on Llama adoption

Update on Llama adoption (ai.meta.com)

136 points by meetpateltech 2 years ago | 155 comments

Screenshot of ai.meta.com: The Llama Ecosystem: Past, Present, and Future

The Llama Ecosystem: Past, Present, and Future (ai.meta.com)

68 points by allanberger 3 years ago | 29 comments

Screenshot of ai.meta.com: Code Llama, a state-of-the-art large language model for coding

Code Llama, a state-of-the-art large language model for coding (ai.meta.com)

911 points by marcopicentini 3 years ago | 74 comments

Meta AI blog post from August 24, 2023 announcing Code Llama, a large language model for code generation built on Llama 2.

code-llama llama meta-ai llm

Screenshot of ai.meta.com: Meta Large Language Model Compiler

Meta Large Language Model Compiler (ai.meta.com)

24 points by marban 2 years ago | 1 comments

Screenshot of ai.meta.com: SceneScript, a novel approach for 3D scene reconstruction

SceneScript, a novel approach for 3D scene reconstruction (ai.meta.com)

109 points by Klaster_1 2 years ago | 23 comments

Related stories

Screenshot of mlops.systems: My finetuned models beat OpenAI's GPT-4

My finetuned models beat OpenAI's GPT-4 (mlops.systems)

376 points by majc2 2 years ago | 86 comments

Blog post evaluating finetuned Mistral, Llama3 and Solar LLMs against OpenAI's GPT-4 on accuracy for structured data extraction from press releases.

fine-tuning llms gpt-4 mistral

Screenshot of replicate.com: Guide to running Llama 2 locally

Guide to running Llama 2 locally (replicate.com)

573 points by bfirsh 3 years ago | 153 comments

Replicate blog post explaining how to run Meta's Llama 2 model locally on M1/M2 Macs, Windows, Linux, and phones without an internet connection.

llama-2 local-llm replicate meta

Screenshot of ai.meta.com: Llama 3.2: Revolutionizing edge AI and vision with open, customizable models

Llama 3.2: Revolutionizing edge AI and vision with open, customizable models (ai.meta.com)

861 points by nmwnmw 2 years ago | 298 comments

Meta AI blog post announcing Llama 3.2, including vision-capable models and lightweight models for edge and mobile devices.

llama meta large-language-models vision-models

Screenshot of twitter.com: Meta AI releases Code Llama 70B

Meta AI releases Code Llama 70B (twitter.com)

448 points by albert_e 2 years ago | 233 comments

A post from Meta AI on X announcing the release of Code Llama 70B, a larger version of its code-generation language model.

code-llama meta-ai llama large-language-models

Screenshot of finbarr.ca: How Is LLaMa.cpp Possible?

How Is LLaMa.cpp Possible?(finbarr.ca)

648 points by birriel 3 years ago | 210 comments

Blog post by Finbarr Timbers explaining the math of why llama.cpp can run LLaMA models locally on consumer hardware, focusing on memory bandwidth and compute limits.

llama-cpp llama llm-inference quantization

Screenshot of ollama.com: Ollama's new engine for multimodal models

Ollama's new engine for multimodal models (ollama.com)

331 points by LorenDB 1 year ago | 73 comments

Ollama blog post from May 15, 2025 announcing a new engine for running multimodal models locally.

ollama multimodal-models local-llm vision-models