Gemma 2 9b is a 9-billion-parameter language model hosted on Hugging Face. It belongs to the class of foundation models and supports the text-generation task.
The model was created by Google and released on the platform in June 2024. It has accumulated over 1.9 million downloads and maintains an active inference status. The repository provides tokenizer configuration that defines special tokens including a beginning-of-sequence token, end-of-sequence token, padding token, and unknown token. Its use_default_system_prompt setting is disabled.
Gemma 2 9b can be accessed through multiple inference providers. One listed provider is featherless-ai, where the model runs with live status for text-generation workloads. The model files are stored in safetensors format. It is available for direct use on the Hugging Face site and through the platform's ecosystem of tools for models, datasets, and spaces.
The entry appears in a catalog that emphasizes open source and open science. No pricing, license text, or explicit target audience is stated on the page.
Gemma 2 9b sits in PulseGate's Foundation models & chat category. It focuses on accessing a capable open-source language model for local or self-hosted text generation without relying on proprietary APIs. It is built as an open-source project for developers. Gemma 2 9b is open source under the Apache-2.0 license. It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by Google (United States), and the product first shipped in 2024. Development happens publicly on GitHub with 383 stars. It operates in a well-populated space: PulseGate tracks 15 similar tools. Key capabilities include text generation, open weights, and instruction tuned.
Latest indexed changes and source events
google/gemma-2-9b verified by the PulseGate indexer
Other apps tracked under the same category.
