Models & Labs
Google Launches Gemini 4 Carbon for High-Throughput Tasks
AI Explainedhigh confidence
Why it matters
- →Provides developers with a cost-effective option for high-volume API calls.
- →Expands the practical utility of the Gemini family beyond flagship reasoning models.
- →Indicates increased competition in the optimized inference market.
Google has announced the general availability of Gemini 4 Carbon, part of its expanding family of specialized models. Designed specifically for high-throughput applications, this model aims to balance performance with cost efficiency for developers handling large-scale inference tasks. The release complements Google's broader strategy of offering tiered model options to suit different computational needs and budget constraints.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from AI Explained
© AI ExplainedResearchresearch
New Benchmarks: ExploitGym, BenchCAD, and IntegrityBench
Several new evaluation benchmarks have been released, including ExploitGym for security vulnerabilities and BenchCAD for design robustness.
AI Explained
© AI ExplainedResearchresearch
METR Report: AI R&D Acceleration at Anthropic
More in Models & Labs
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
llama.cpp Releases
Models & Labscoding
llama.cpp b12342 adds few-row MMQ for speculative decoding
Speculative decoding just got a significant speed boost on NVIDIA GPUs. This release introduces a specialized kernel for 'few-row' matrix multiplications, targeting the small batch sizes typical of verification passes in speculative decoding workflows. By optimizing these specific operations for quantized formats like Q8_0 and IQ4 variants, llama.cpp reduces latency where it matters most during token generation. The change is CUDA-only for now but leverages hardware capabilities from Ampere onwards, making local inference faster without requiring new model architectures or complex configuration changes.
