Models & Labs
Google Runs Gemma 4 in Orbit
Lev Selectorhigh confidence
Why it matters
- →First major LLM run in space
- →Validates edge AI for satellite connectivity
- →Expands use cases for offline/independent AI systems
Google has achieved a milestone by running the Gemma 4 large language model on hardware located in orbit. This deployment tests the viability of edge AI in extreme environments, specifically for satellite operations where latency and bandwidth are constrained. The move underscores Google's commitment to expanding the physical boundaries of AI inference beyond terrestrial data centers.
Read originalThe story around this
TopicOrbital Artificial IntelligenceRising
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Google DeepMind Unveils Gemini Robotics 2
WIRED AI · July 30, 2026 · Background
- 2Deep Learning Maps Methane Emissions from Space
Google Research Blog · September 1, 2026 · Background
- 3Google's August AI Innovations: Gemini and Beyond
Google AI Blog · September 1, 2026 · Background
- 4Satlyt raises $8M for orbital AI software
TechCrunch AI · October 1, 2026 · Related
- 5Google Announces Gemini 4 Argon with 1M Token Output
Sam Witteveen · October 1, 2026 · Background
- 6Google Deploys First AI Chips in Orbit
The AI Daily Brief · October 3, 2026 · Same story
- 7Google Gemini 4 Carbon wins benchmarks
Matthew Berman · October 29, 2026 · Related
- 8Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Matt Wolfe · October 30, 2026 · Background
Follow this story
Open the full story →Google's Suncatcher satellite runs AI inference in orbit
4 developments
- Oct 30 · TechCrunch AI
Google's Suncatcher satellite runs AI inference in orbit - Oct 30 · The Verge AI
Google boots TPU AI server in orbit - Nov 2 · The Rundown AI
AI backlash hits polls; Google tests space AI↳ Roughly 20 communities vote on data center bans as OpenAI rebrands facilities to mitigate public anger - Nov 6 · Lev Selector
Google Runs Gemma 4 in Orbit (This article)↳ Google deploys the Gemma 4 model on satellites to test AI inference in orbit.
More from Lev Selector
© Lev SelectorVideo & Creative AIimage
OpenAI Images 2.6 Released
OpenAI has updated its image generation model to version 2.6, bringing improvements in quality and consistency.
Lev Selector
© Lev SelectorOpen Sourceimage
FLUX 3 Image Klein Open Weights Released
Black Forest Labs released FLUX 3 Image Klein, an open-weight image generation model offering high-quality results for developers.
Lev Selector
© Lev SelectorGeneral AIagents
Siri AI Opens to Developers
Apple has opened its Siri AI capabilities to third-party developers, expanding the ecosystem of voice-activated integrations.
Lev Selector
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
llama.cpp Releases
Models & Labsother
llama.cpp b12182 release with CUDA 13 and ROCm 10
This release quietly cements llama.cpp as the universal inference runtime by adding default builds for CUDA 13.5 and ROCm 10.0 across Linux and Windows. The inclusion of ROCm 10 means AMD GPU users no longer need custom compilation to access modern acceleration, effectively closing the gap with NVIDIA's ecosystem support. While KleidiAI on Apple Silicon is disabled in this build, the broader platform coverage ensures that local inference remains accessible on virtually any hardware configuration without manual setup.
llama.cpp Releases