Models & Labs
b9070 release adds Q4_0 MoE GEMM for Adreno
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances performance for Adreno GPU users, crucial for mobile development.
- →Streamlines codebase with technical adjustments, improving efficiency.
- →Expands platform support, making the tool more accessible.
The latest b9070 release of llama.cpp brings Q4_0 MoE GEMM support for Adreno GPUs, enhancing performance for mobile developers using Qualcomm's graphics. This update, co-authored by Li He from Qualcomm, includes technical refinements like whitespace fixes and code cleanup. The release supports a wide range of platforms, including macOS, Linux, Windows, and Android, ensuring broad accessibility. This update focuses on optimizing existing capabilities rather than introducing new models.
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.
What happened next
- 1Llama.cpp b9127 Release Adds Adreno xmem GEMM
llama.cpp Releases · May 13, 2026 · Same story
- 2Llama.cpp Adds Adreno Support with New Kernels
llama.cpp Releases · June 12, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 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 were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
