gemma
30 articles about gemma in AI news
Google Open-Sources DiffusionGemma, 26B Model Hits 1K Tokens/Sec on H100
Google open-sourced DiffusionGemma, a 26B-parameter diffusion text model hitting 1,000 tokens/sec on H100 — 4x faster than autoregressive models, but with lower quality.
mlx-vlm v0.6.2 Adds Gemma 4 QAT Support for Local GPUs
mlx-vlm v0.6.2 adds launch-day support for Google DeepMind's Gemma 4 QAT checkpoints, enabling local inference on consumer GPUs and edge devices with video input for the 12B model.
Google Gemma 4 12B: Encoder-Free Multimodal Model Launches
Google launched Gemma 4 12B, an encoder-free multimodal model for on-device AI, reducing latency by eliminating the vision encoder.
Ollama Now Runs Codex Locally: DeepSeek V4, Gemma 4, Qwen 3.6 Supported
Ollama integrates Codex support for DeepSeek V4, Gemma 4, Qwen 3.6, enabling free local code generation, challenging OpenAI's API model.
Google Gemma 4: 3x Faster Inference with MTP Drafters
Google's Gemma 4 claims up to 3x faster inference via MTP drafters, but released no benchmark numbers or architectural details.
Gemma 4 Hits 50M Downloads in Weeks, Google's Fastest Launch
Gemma 4 downloaded 50M+ times in weeks, fastest Google open model launch, outpacing Gemma 3 by ~3x.
Developer Swaps Dash Cam Analysis for Gemma 4 & Falcon Perception
A developer announced they are replacing their entire dash cam video analysis system with Google's Gemma 4 and Falcon Perception models, signaling a practical shift towards newer, specialized multimodal models for real-time edge applications.
Gemma 4 Integrates SAM 3.1 for Subject-Aware Image Masking
A new demo shows Google's Gemma 4 vision-language model using Meta's SAM 3.1 to identify and segment primary subjects in complex scenes, like a child with dogs. This represents a practical integration of specialized vision models into multimodal reasoning workflows.
Unsloth Offers Free Fine-Tuning for Google Gemma 4 via Colab Notebook
Unsloth has released a Colab notebook enabling free fine-tuning of Google's Gemma 4 model. This simplifies the process of customizing a state-of-the-art open-weight LLM using just a browser.
MedGemma 1.5 Technical Report Released, Details Multimodal Medical AI
Google DeepMind has published the technical report for MedGemma 1.5, detailing the architecture and capabilities of its open-source, multimodal medical AI model. This follows the initial Med-PaLM 2 release and represents a significant step in making specialized medical AI more accessible.
Google's Gemma 4B Model Runs on Nintendo Switch at 1.5 Tokens/Second
A developer successfully ran Google's 4-billion parameter Gemma language model on a Nintendo Switch, achieving 1.5 tokens/second inference. This demonstrates the increasing feasibility of running small LLMs on consumer-grade edge hardware.
MLX-LM v0.9.0 Adds Better Batching, Supports Gemma 4 on Apple Silicon
Apple's MLX-LM framework released version 0.9.0 with enhanced server batching and support for Google's Gemma 4 model, improving local LLM inference efficiency on Apple Silicon. This update addresses a key performance bottleneck for developers running models locally on Mac hardware.
Gemma4 + Falcon Perception Enables Vision-Action Agent Pipeline
A developer shared a pipeline where Gemma4 interprets images, Falcon Perception segments objects with metadata, and Gemma4 reasons to call tools. This demonstrates a modular approach to vision-language-action agents.
Ethan Mollick: Gemma 4 Impressive On-Device, But Agentic Workflows Doubted
Wharton professor Ethan Mollick finds Google's Gemma 4 powerful for on-device use but is skeptical about its ability to execute true agentic workflows, citing limitations in judgment and self-correction.
Gemma 4 Integrated into Android Studio for AI-Assisted App Development
Google has integrated its Gemma 4 language model into Android Studio's Agent mode, providing developers with AI-assisted coding features like refactoring and feature development within the official Android IDE.
Gemma 4 Ported to MLX-Swift, Runs Locally on Apple Silicon
Google's Gemma 4 language model has been ported to the MLX-Swift framework by a community developer, making it available for local inference on Apple Silicon Macs and iOS devices through the LocallyAI app.
Gemma 4 26B A4B Hits 45.7 tokens/sec Decode Speed on MacBook Air via MLX Community
A community benchmark shows the Gemma 4 26B A4B model running at 45.7 tokens/sec decode speed on a MacBook Air using the MLX framework. This highlights rapid progress in efficient local deployment of mid-size language models on consumer Apple Silicon.
Atomic Chat Launches Hermes Agent: A Free, Local Agent Stack Powered by Gemma 4
Atomic Chat has launched Hermes Agent, an open-source agent stack powered by Google's Gemma 4 model that runs entirely locally and is free to use. This makes advanced AI agent functionality accessible without cloud dependencies or API costs.
Google's Gemma4 Models Lead in Small-Scale Open LLM Performance, According to Developer Analysis
Independent developer analysis indicates Google's Gemma4 models are currently the top-performing open-source small language models, with a significant lead in model behavior over alternatives.
Gemma 4 Demonstrates Self-Terminating Loop Detection in Code Execution, User Reports
A developer shared an observation that Google's Gemma 4 model recognized it was stuck in an infinite loop during a coding task and stopped itself. This represents a potential advance in AI's ability to monitor and control its own execution state.
Google Releases Gemma 4 Family Under Apache 2.0, Featuring 2B to 31B Models with MoE and Multimodal Capabilities
Google has released the Gemma 4 family of open-weight models, derived from Gemini 3 technology. The four models, ranging from 2B to 31B parameters and including a Mixture-of-Experts variant, are available under a permissive Apache 2.0 license and feature multimodal processing.
Google Gemma 4 Model Reportedly in Testing, Signaling Next-Gen Open-Weight LLM Release
A developer reports that Google's Gemma 4 model is 'incoming' and currently being tested. This suggests the next iteration of Google's open-weight language model family is nearing release.
MiRA Framework Boosts Gemma3-12B to 43% Success Rate on WebArena-Lite, Surpassing GPT-4 and WebRL
Researchers propose MiRA, a milestone-based RL framework that improves long-horizon planning in LLM agents. It boosts Gemma3-12B's web navigation success from 6.4% to 43%, outperforming GPT-4-Turbo (17.6%) and the previous SOTA WebRL (38.4%).
ReXInTheWild Benchmark Reveals VLMs Struggle with Medical Photos: Gemini-3 Leads at 78%, MedGemma Trails at 37%
Researchers introduced ReXInTheWild, a benchmark of 955 clinician-verified questions based on 484 real medical photographs. Leading multimodal models show wide performance gaps, with Gemini-3 scoring 78% accuracy while the specialized MedGemma model achieved only 37%.
Fine-Tuning Gemma 3 1B-IT for Financial Reasoning with QLoRA
A technical guide details using QLoRA and reasoning-augmented data to fine-tune Google's Gemma 3 1B-IT model for financial analysis. This demonstrates a method to specialize small language models for complex, domain-specific tasks.
Google's Gemma 4 Emerges: The Next Generation of Open AI Models
Google has announced the upcoming release of Gemma 4, the next iteration of its open-source AI model family. This development signals Google's continued commitment to accessible AI technology and intensified competition in the open model space.
Atomic Chat's TurboQuant Enables Gemma 4 Local Inference on 16GB MacBook Air
Atomic Chat's new TurboQuant algorithm aggressively compresses the KV cache, allowing models requiring 32GB+ RAM to run on 16GB MacBook Airs at 25 tokens/sec, advancing local AI deployment.
SAEs Predict Agent Tool Failures Before Execution, Paper Shows
SAE-based probes predict agent tool failures before execution, tested on GPT-OSS and Gemma 3. Adds internal observability missing from current external methods.
mlx-vlm v0.5.0 Adds Continuous Batching, Distributed Inference for Apple Silicon
mlx-vlm v0.5.0 adds continuous batching, speculative decoding, and distributed inference for Apple Silicon. The release supports Qwen3.5, Kimi K2.5, Gemma 4 video, and new models with 21 contributors.
MLX-VLM Adds Continuous Batching, OpenAI API, and Vision Cache for Apple Silicon
The next release of MLX-VLM will introduce continuous batching, an OpenAI-compatible API, and vision feature caching for multimodal models running locally on Apple Silicon. These optimizations promise up to 228x speedups on cache hits for models like Gemma4.