• About
  • Contact
  • Advertise
  • Privacy Policy
  • Terms Of Use
Tuesday, July 8, 2025
No Result
View All Result
Converseer
  • Home
  • News
    • General News
    • Education
    • Business
    • Security
    • Entertainment
    • Lifestyle
    • Tourism
  • Politics
  • Metro
  • Jobs
  • Sports
  • Health
  • Tech
  • More
    • Science & Nature
    • Agriculture
    • Opinion
    • Feature
    • Fact Check
    • History
    • Profile & Biography
    • Special Reports
  • Home
  • News
    • General News
    • Education
    • Business
    • Security
    • Entertainment
    • Lifestyle
    • Tourism
  • Politics
  • Metro
  • Jobs
  • Sports
  • Health
  • Tech
  • More
    • Science & Nature
    • Agriculture
    • Opinion
    • Feature
    • Fact Check
    • History
    • Profile & Biography
    • Special Reports
No Result
View All Result
Converseer
No Result
View All Result

Google releases Gemma 2 open source AI model with 9/27 billion parameters: performance is better than its peers and can be run on a single A100/H100 GPU

by Editorial Team
24 September 2024
in Tech
Gemma 2 Google releases Gemma 2 open source AI model with 9/27 billion parameters: performance is better than its peers and can be run on a single A100/H100 GPU

Google issued a press release yesterday, releasing the Gemma 2 large language model to researchers and developers around the world . It comes in two sizes: 9 billion parameters (9B) and 27 billion parameters (27B).

Compared with the first generation, the Gemma 2 large language model has higher reasoning performance and efficiency, and has made significant progress in security.

Google said in a press release that the performance of the Gemma 2-27B model is comparable to mainstream models twice its size, and this performance can be achieved with just one NVIDIA H100 ensor Core GPU or TPU host, greatly reducing deployment costs.

The Gemma 2-9B model outperforms Llama 3 8B and other open source models of similar size. Google also plans to release a Gemma 2 model with 2.6 billion parameters in the coming months, which is more suitable for AI application scenarios on smartphones.

Google said it has redesigned the overall architecture for Gemma 2 to achieve excellent performance and reasoning efficiency. IT Home attached the main features of Gemma 2 as follows:

Excellent performance:

The 27B version is the best performer in its size class, even more competitive than models twice its size. The 9B version is also the best performer in its class, outperforming the Llama 3 8B and other open models of the same size.

format,f webp Google releases Gemma 2 open source AI model with 9/27 billion parameters: performance is better than its peers and can be run on a single A100/H100 GPU

Efficiency and cost:

The 27B Gemma 2 model can efficiently run inference at full precision on a single Google Cloud TPU host, NVIDIA A100 80GB Tensor Core GPU, or NVIDIA H100 Tensor Core GPU, maintaining high performance while significantly reducing costs. This makes AI deployment more accessible and budget-friendly.

READ ALSO:
  • Shooting Brake? Ferrari’s first all-electric car spy photos revealed
  • Top 10 predictions for debate between Donald Trump and Joe Biden
  • LeBron James’ son Bronny James drafted by Los Angeles Lakers

Fast inference across hardware

Gemma 2 is optimised to run at blazing speeds on a wide range of hardware, from powerful gaming laptops and high-end desktops to cloud-based setups.

Try Gemma 2 at full precision in Google AI Studio, unlock native performance on your CPU using the quantised version of Gemma.cpp , or try it on your home PC with NVIDIA RTX or GeForce RTX with Hugging Face Transformers.

Tags: Google NewsWorld News

Related News

Acer Go Pro Notebook with i5-13420H, 16GB RAM, and 1TB Storage Now Available
Tech

Acer Go Pro Notebook with i5-13420H, 16GB RAM, and 1TB Storage Now Available

6 months ago
Samsung to redesign Galaxy Buds 3 earphones
Tech

Samsung to redesign Galaxy Buds 3 earphones

1 year ago
DeepSeek: Chinese AI Startups See Surge in Funding After Spring Festival
Tech

DeepSeek: Chinese AI Startups See Surge in Funding After Spring Festival

4 months ago
Microsoft announces revenue of US$61.9bn, 17% increase in Q1 2024
Tech

Microsoft announces revenue of US$61.9bn, 17% increase in Q1 2024

1 year ago
Politics

Mozambique restricts social media amid election disputes and tensions

8 months ago
Cities: Skylines 2 receives Beach Asset Pack free DLC, DLSS 2 support
Tech

Cities: Skylines 2 receives Beach Asset Pack free DLC, DLSS 2 support

1 year ago

Latest News

Poland defends new border checks as German officials warn of fallout

JAMB releases 2025 mop-up UTME results, records only 12% turnout

Olubadan of Ibadanland, Oba Owolabi Olakulehin, dies at 90

Cross River Chief of Staff reaffirms loyalty to Governor Otu, donates to church

Calls intensify for NOUN study centre in Ogoja

Mbappé’s bicycle kick seals Real Madrid’s 3-2 win over Dortmund

About Us

Converseer is an online newspaper that delivers impartial, comprehensive news coverage on politics, business, health, tech, metro, and education, among other topics.

Social Media

  • Facebook
  • WhatsApp
  • X (Twitter)
  • YouTube
  • Telegram

Coverage

  • Africa
  • Americas
  • Asia
  • Europe
  • Middle East

Special Pages

  • Special Reports
  • Fact Check
  • Feature
  • Opinion
  • History
  • About
  • Contact
  • Advertise
  • Privacy Policy
  • Terms Of Use

© 2025 Converseer - All Rights Reserved.

No Result
View All Result
  • Home
  • News
    • General News
    • Education
    • Business
    • Security
    • Entertainment
    • Lifestyle
    • Tourism
  • Politics
  • Metro
  • Jobs
  • Sports
  • Health
  • Tech
  • More
    • Science & Nature
    • Agriculture
    • Opinion
    • Feature
    • Fact Check
    • History
    • Profile & Biography
    • Special Reports

© 2025 Converseer - All Rights Reserved.