POCKET-35B-GGUF is a quantized version of a 35 billion parameter language model in GGUF format. It is designed for efficient local inference using tools such as llama.cpp. The model includes a detailed chat template supporting multimodal content and tool use.
In the Foundation models & chat space, POCKET 35B takes a focused approach. It focuses on running a 35 billion parameter model efficiently on consumer hardware. It is built as an open-source project for local LLM users and developers. POCKET 35B is open source under the MIT license. It ships for the command line.
Behind POCKET 35B is FINAL-Bench, and it first shipped in 2023. The project is developed in the open on GitHub with 122.7k stars and 1.2k commits in the last 90 days.
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