Tag

Ollama

All articles tagged with #ollama

Ollama flaw could leak memory and expose secrets via crafted GGUF files
security21 days ago

Ollama flaw could leak memory and expose secrets via crafted GGUF files

A high-severity heap out-of-bounds read in Ollama's GGUF model loader (CVE-2026-7482, CVSS 9.1) lets remote, unauthenticated attackers leak the Ollama process memory by sending a crafted GGUF to /api/create, potentially exposing environment variables, API keys, prompts, and user data across 300k+ servers. Mitigations include applying fixes, restricting network exposure, and deploying a proxy/auth gateway. The article also cites two unpatched Windows updater flaws (CVE-2026-42248/42249) that can enable persistent code execution; recommended workarounds are to disable automatic updates and remove Startup-folder shortcuts until patches land.

"Run an LLM Locally on Your PC in Under 10 Minutes with These Simple Steps"
technology2 years ago

"Run an LLM Locally on Your PC in Under 10 Minutes with These Simple Steps"

It's possible to run large language models (LLMs) like Mistral or Codellama on your PC using tools like Ollama, LM Suite, and Llama.cpp, with support for Nvidia and Apple's M-series GPUs as well as AVX2-compatible CPUs. Ollama can be installed on Windows, Linux, and Mac, and offers various models and quantization options to optimize performance based on system resources. The article provides instructions for installing Ollama, running models, and managing installed models, and suggests exploring other frameworks for running local LLMs if needed.