Search

Showing top 77 results for "Gemma 4 releases" · filtered from 81 indexed

Google Gemma

Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.

130 articles indexed Last updated 1d ago See topic hub

Google releases Gemma 4, a family of open models built off of Gemini 3 - Engadget

Google releases Gemma 4, a family of open models built off of Gemini 3 The new systems are all available under the Apache 2.0 license. …

Apr 2, 2026 · Igor Bonifacic

Google's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM

… Google has released optional MTP versions of the other Gemma 4 models, but this is the first one to have MTP out of the box. Gemma 4 12B is also more efficient thanks to a new approach to multimodality. The Gemma 4 family is natively multimodal, accepting text, audio, or images as inputs. …

Jun 3, 2026 · Ryan Whitwam

Google's Gemma 4 AI models get 3x speed boost by predicting future tokens

… Gemma allows users to tinker with AI on their hardware rather than sharing all their data with a cloud AI system from Google or someone else. Google also changed the license for Gemma 4 to Apache 2.0, which is much more permissive than the custom Gemma license Google employed for previous releases. …

May 6, 2026 · Ryan Whitwam

Run Google's Gemini LLMs right on your Mac with the new AI Edge Gallery

… The model joins existing Gemma 4 models as well as existing Gemma 3n models. Gemma-4-12B-it Gemma-4-E2B-it Gemma-4-E4B-it Gemma-3n-E2B-it Gemma-3n-E4B-it The new Gemma 4 12 B model will offer "agentic multimodal intelligence" that is designed to be run "directly" on laptops. …

Jun 4, 2026 · Oliver Haslam

AMD Rolls Out Gemma 4 Model Support Across Full Range of GPUs & CPUs

… Point Lemonade to the ROCm build by setting the environment variable: export LEMONADE LLAMACPP ROCM BIN=/path/to/llama-server Start Lemonade and load the Gemma 4 model via the API: lemonade-server serve curl http://localhost:8000/api/v1/pull \ -H "Content-Type: application/json" \ -d '{"model name"… …

Apr 4, 2026 · Hassan Mujtaba

Welcome Gemma 4: Frontier multimodal intelligence on device

… "mlx-community/gemma-4-26b-a4b-bf16" instead of "mlx-community/gemma-4-26B-A4B-it" The following command worked for me: ▶ mlx vlm.generate \ --model "mlx-community/gemma-4-26b-a4b-it-4bit" \ --prompt "What is the capital of France?" \ --kv-bits 3.5 \ --kv-quant-scheme turboquant Hi All Struggling t… …

Apr 12, 2026 · merve

Google's latest on-device AI model is custom-made for your laptop

… What that means is that Gemma 4 12B can handle multimodal inputs, just like the other Gemma models, but without the added overhead of encoding such inputs. …

Jun 4, 2026 · Akshay Gangwar

Google AI Edge Gallery launches to macOS - 9to5Mac

… Google AI Edge Gallery and Gemma 4 12B One thing to note right from the get-go is that, contrary to Ollama and LM Studio, which allow users to install any AI model compatible with their hardware, Google AI Edge Gallery for Mac currently only offers access to 5 of Google’s own models, where ‘it’ sta… …

Jun 4, 2026 · Marcus Mendes

Google announces open Gemma 4 model with Apache 2.0 license

Google announces open Gemma 4 model with Apache 2.0 license Abner Li | Apr 2 2026 - 9:00 am PT | Apr 2 2026 - 9:00 am PT Google today announced Gemma 4 as its latest open model . …

Apr 2, 2026 · Abner Li

Google battles Chinese open weights models with Gemma 4

AI + ML Google battles Chinese open-weights models with Gemma 4 Now with a more permissive license, multi-modality, and support for more than 140 languages Google on Thursday unleashed a wave of new open-weights Gemma models optimized for agentic AI and coding, under a more permissive Apache 2.0 li… …

Apr 2, 2026 · Tobias Mann

Followed topics