This collection provides GGUF-quantized versions of Llama-3-8B-Instruct with a 64k token context window. Hosted by MaziyarPanahi, it enables users to run the model locally using llama.cpp, Ollama, and similar tools. It is ideal for applications requiring longer context while maintaining reasonable hardware requirements.
Llama 3 8B Instruct 64k sits in PulseGate's Foundation models & chat category. It focuses on running an 8B-parameter Llama 3 model with long-context support (64k tokens) locally without cloud dependency. Llama 3 8B Instruct 64k is an open-source project aimed at developers. Llama 3 8B Instruct 64k is open source under the MIT license. It runs on the web, the command line, and API, and it can be self-hosted.
MaziyarPanahi builds and maintains Llama 3 8B Instruct 64k, and it first shipped in 2023. Development happens publicly on GitHub with 122.3k stars and 1.2k commits in the last 90 days. PulseGate's similarity index places it among 12 comparable projects. Among its 4 catalogued features are extended context, GGUF formats, and instruction model. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do