Models & Labs
llama.cpp adds Clover MoE model support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables local inference for the Clover MoE architecture on consumer hardware.
- →Adds GGUF conversion support, allowing easy integration into existing workflows.
- →Demonstrates llama.cpp's expanding capability to handle hybrid and non-standard attention mechanisms.
The llama.cpp project has released an update adding support for the Clover Mixture of Experts (MoE) model architecture. The implementation includes GGUF conversion capabilities, model loading logic, and causal hybrid attention mechanisms, leveraging shared helpers for recurrent states and LoRA. This addition allows users to run Clover models locally across a wide range of hardware, including NVIDIA CUDA 13, AMD ROCm 10, and Apple Silicon devices. The update is part of ongoing efforts to broaden llama.cpp's compatibility beyond standard transformer architectures.
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 b11081 release with CUDA 13 and ROCm 10 support
llama.cpp Releases · September 22, 2026 · Same story
- 2llama.cpp v0.7.0: MoE caching and speculative decoding advances
llama.cpp Releases · October 16, 2026 · Same story
Follow this story
Open the full story →llama.cpp b12027 adds CUDA 13 and Snapdragon support
2 developments
- Nov 1 · llama.cpp Releases
llama.cpp b12027 adds CUDA 13 and Snapdragon support - Nov 3 · llama.cpp Releases
llama.cpp adds Clover MoE model support (This article)↳ llama.cpp adds native support for Clover MoE model with causal hybrid attention and GGUF conversion tools
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12053 updates Apple memory and adds ROCm 10
This release quietly fixes a memory allocation quirk on Apple Silicon by switching to vm_allocate, which should stabilize buffer handling across macOS and iOS. More notably, it brings ROCm 10.0 support to both Linux and Windows, finally giving AMD GPU users parity with CUDA builds in the standard distribution. The update also extends CUDA 13 compatibility to ARM64 architectures, broadening the hardware base for high-performance inference. It’s a maintenance-heavy release that solidifies llama.cpp as a cross-platform runtime rather than just a local Mac tool.
llama.cpp Releases
Models & Labsother
llama.cpp b12054 adds CUDA 13 and ROCm 10.0
This release quietly cements llama.cpp as the universal inference runtime by adding default support for CUDA 13 and ROCm 10.0. NVIDIA users can now leverage newer driver stacks without waiting for separate builds, while AMD GPU owners finally get parity with modern ROCm versions. The inclusion of Snapdragon and OpenVINO binaries further widens the hardware net, though Apple Silicon KleidiAI is notably disabled here. It’s less about new features and more about ensuring no major accelerator is left behind in the local LLM ecosystem.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12057 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing first-class ROCm 10.0 support to both Linux and Windows. AMD GPU users no longer need workarounds, effectively closing a long-standing parity gap with NVIDIA's CUDA ecosystem. Equally notable is the new Snapdragon build for Linux, which unlocks local AI on ARM-based laptops using Adreno GPUs and Hexagon NPUs. While KleidiAI on Apple Silicon is temporarily disabled, the expansion into AMD and Qualcomm hardware signals a strategic shift toward broadening accessible local inference beyond just NVIDIA.
llama.cpp Releases
More in Models & Labs
Models & Labscoding
vLLM v0.33.0: Blackwell & DeepSeek V4.1 Optimizations
vLLM v0.33.0 is a massive infrastructure update that finally brings first-class support for NVIDIA's Blackwell architecture and the new DeepSeek V4.1 models. The release drops CUDA 12.9 in favor of CUDA 13.0, signaling a hard pivot to next-gen hardware while adding critical optimizations like block-diffusion drafters and quantized LM heads that significantly boost decode throughput. AMD users also get major wins with ROCm 10.0 defaults and MonoKernel decoding on MI355X. This isn't just another version bump; it's the runtime catching up to the bleeding edge of model complexity and silicon capability.
vLLM Releases
© TechCrunch AIModels & Labsother
Apple Watch Audio Intelligence Beta Begins
Apple is finally testing the AI features that define its wearable strategy. Live Rewind and Siri Recaps turn the Apple Watch into a passive conversation recorder, using on-device detection to buffer audio before sending it to Private Cloud Compute for summarization. The privacy architecture is aggressive: raw audio never leaves the secure enclave, and summaries are ephemeral by default. This marks the first time ambient AI recording has moved from prototype to consumer beta on a mainstream device.
TechCrunch AI
© AI ExplainedModels & Labsmodels
OpenAI Addresses Safety Issues Ahead of Next Flagship
Reports indicate OpenAI is scrambling to fix safety issues in its training environment before shipping its next flagship model.
AI Explained