Models & Labs
llama.cpp b10232 release enhances Metal support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances performance on macOS and iOS with optimized Metal support.
- →Expands compatibility across multiple operating systems and hardware configurations.
- →Strengthens llama.cpp's position as a versatile inference runtime.
The b10232 release of llama.cpp focuses on enhancing Metal support with the implementation of DeepSeek V4 hyper-connections. This update includes optimized kernels for SIMDgroup register and shuffle, specifically benefiting macOS and iOS platforms. Additionally, the release broadens compatibility across multiple operating systems, including Ubuntu and Windows, with optimizations for Vulkan, ROCm, and CUDA. These improvements solidify llama.cpp's role as a flexible inference runtime for various hardware setups.
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.
How we got here
- 1llama.cpp b10159 release enhances Metal backend
llama.cpp Releases · July 29, 2026 · Same story
What happened next
- 2llama.cpp b10590 Release Expands Platform Support
llama.cpp Releases · August 24, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b11332 adds ROCm 10 and Snapdragon support
This release quietly expands llama.cpp's hardware reach with two major additions: ROCm 10.0 for AMD GPUs and native support for Linux arm64 Snapdragon devices. The inclusion of ROCm 10 is significant, as it brings AMD users closer to parity with CUDA in terms of supported versions, reducing the friction for local inference on non-NVIDIA hardware. Meanwhile, Snapdragon support opens up a new class of mobile AI acceleration, allowing developers to leverage Adreno GPUs and Hexagon NPUs directly. While Apple Silicon builds have KleidiAI disabled by default, the core value here is the broadening of accessible compute backends without requiring complex custom compilation.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11333 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who previously lagged behind NVIDIA. The standout addition is native support for Linux arm64 Snapdragon devices, enabling local AI on mobile-class silicon with CPU, Adreno GPU, and Hexagon NPU acceleration. While KleidiAI on Apple Silicon is currently disabled in this build, the broader expansion to diverse accelerators means developers no longer need to compile from source to target non-NVIDIA hardware. The world now has a single binary ecosystem that runs everywhere from x86 servers to ARM mobile chips.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11334 fixes Metal buffer leaks
This release addresses a memory management issue in the Metal backend by properly releasing temporary private transfer buffers. While not a feature upgrade, it stabilizes performance on Apple Silicon devices where previous builds might have suffered from memory pressure or fragmentation during inference. The update also includes standard platform binaries for CUDA 13 and ROCm 10.0, ensuring compatibility with the latest NVIDIA and AMD driver stacks. For local LLM users on macOS, this is a quiet but necessary maintenance step to keep inference smooth.
llama.cpp Releases
More in Models & Labs
© The Verge AIModels & Labsother
Google launches Guided Vision in Gemini Live
Google is bringing real-time audio scene description to Android via Gemini Live, directly challenging Apple’s VoiceOver Live Recognition. This feature targets users with low vision by providing immediate audio cues and follow-up Q&A capabilities for physical objects. It integrates deeply into the accessibility ecosystem through TalkBack, moving beyond simple text reading to contextual environmental awareness. The move signals a shift toward multimodal AI as a standard utility for daily navigation rather than just a novelty.
The Verge AI
© TechCrunch AIModels & Labsagents
AWS releases open-source Strands Decider 2B
Amazon’s Strands Decider 2B joins the growing wave of decision models designed to replace heavy LLMs for simple routing tasks. Built on Qwen3.5-2B, it outputs calibrated choices with confidence scores rather than generating text, offering a cheaper, faster alternative for agentic workflows. The release signals AWS’s push into specialized agent infrastructure, aiming to solve the latency and cost bottlenecks of general-purpose models. While TypeSafe’s Jev pioneered this space, Amazon’s entry brings enterprise-grade credibility and open-source accessibility to a niche that is rapidly filling with experimental clones.
TechCrunch AI
© Sam WitteveenModels & Labsmodels
Google Announces Gemini 4 Argon with 1M Token Output
Google is pushing the boundaries of context windows with Gemini 4 Argon, a new model capable of generating up to one million tokens in a single response. This isn't just about reading long documents; it's designed for complex agentic workflows where the AI must produce extensive codebases or detailed reports without truncation. Early benchmarks suggest it aims to reclaim top-tier intelligence status against competitors like GPT-6, specifically targeting tasks that require sustained reasoning and massive output generation. The shift from 64K caps to a million-token horizon fundamentally changes how developers might architect multi-step autonomous systems.
Sam Witteveen