Models & Labs
Llama.cpp b9080 Release Enhances Compatibility
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform compatibility, enhancing developer flexibility.
- →Fixes technical issues, improving model integration and performance.
- →Supports a wider range of hardware, broadening usability.
The b9080 release of llama.cpp has been announced, featuring support for the Gemma4_26B_A4B_NVFP4 model. This update addresses several technical issues, including checkpoint conversion fixes, and expands platform compatibility. Developers can now utilize llama.cpp on macOS, Linux, Windows, and Android, with specific enhancements for Apple Silicon and Vulkan support. This release aims to improve the tool's versatility and performance across different systems.
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 b9081 Release Expands Platform Support
llama.cpp Releases · May 9, 2026 · Same story
What happened next
- 2llama.cpp b9855 Release Expands Platform Support
llama.cpp Releases · July 2, 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.
