Text · Released Jul 2024
Meta Llama 3.1 8B
Meta's 8B instruction-tuned model with 128K context and strong general reasoning.
From Meta, Llama 3.1 8B is an open-weight text model. It takes a text prompt and replies with generated text. It runs entirely on your own hardware through Ollama: no API key and no per-use fees.
Supported OS
macOSWindowsLinux
Minimum machine configuration
16 GB RAM · 128K ctx · text · CPU/GPU
Download size · ~4.9 GB
Specs
- Released
- 2 years ago (Jul 2024)
- Pricing
- Free, runs on your hardware
About the creator
Meta
Meta's FAIR and GenAI labs build the open-weight Llama family of language models — among the most widely used open models for local inference.
ai.meta.com ↗More from Meta
Muse Image
ImageCloud
Meta Superintelligence Labs' agentic image model, which plans a layout and calls search and coding tools before it renders, for prompt-faithful generation, multi-reference composition and precise local edits.
Muse Voice Transcribe 1.0
AudioCloud
Meta's speech-to-text model for push-to-talk and speaker-aware transcription, which returns plain text.
Llama 3.2 1B
TextLocal
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
Llama 3.2 3B
TextLocal
Meta's compact 3B instruction-tuned model — fast on-device text generation.
Muse Glimmer
TextLocal
Meta Superintelligence Labs' 30B multimodal model for always-on local agents — tuned for tool use, long tasks, and failure recovery.
From the blog