News
Ollama 0.30 improves GGUF compatibility and GPU performance
Ollama 0.30 integrates newer llama.cpp work, enables Vulkan by default, and reports higher throughput on supported NVIDIA hardware.
OllamaLocal LLMGGUF
Ollama 0.30 improves GGUF model compatibility through llama.cpp and enables Vulkan by default for broader GPU acceleration across supported AMD and Intel hardware.
Ollama reports up to 20% faster NVIDIA throughput in its published Gemma 4 26B test. That figure describes the vendor’s stated test configuration and should not be treated as a universal improvement.
Why it matters: Broader hardware support lowers the barrier to local inference, but actual gains remain dependent on the model, quantization, GPU, context length, and workload.
Source attribution
Original reporting and release information: Ollama Blog.