Linux Graphics & Gaming News
Ollama recently released version 0.40.5, introducing support for NVIDIA's Nemotron 3.5 Super and Nemotron 3.5 Bolt vision-language models (VLMs). Nemotron 3.5 Super is a 120-billion-parameter hybrid M...
Read more →AMD is implementing a new PerfOpt feature within the upcoming Linux 7.4 kernel, designed to enhance AI and Large Language Model (LLM) performance on Radeon integrated graphics processors. As reported ...
Read more →The AMD-aligned Lemonade open-source project, which functions as a local AI server, released version 2026.39.1 today and a release candidate for 2026.40. These updates introduce a new versioning schem...
Read more →Ollama, the tool for running large language models (LLMs) locally, has released version v0.34.4-rc0 today. This release candidate addresses intermittent "model not found" errors, aiming to improve the...
Read more →Linus Torvalds today announced the release of Linux 7.3-rc4. This development snapshot continues to incorporate a significant number of fixes found across the kernel codebase, a trend largely driven b...
Read more →Ollama released version 0.34.0 today, significantly enhancing its integration capabilities. The headline feature allows users to directly employ Ollama models within ChatGPT Desktop, facilitating the ...
Read more →Lemonade 11.9, an AMD-backed open-source local AI server solution, was released today. The software is designed for "100% free and private" AI use, leveraging local hardware including GPUs, CPUs, and ...
Read more →Ollama, the open-source tool for running large language models locally, released version v0.33.3-rc0 today. This release candidate focuses on internal updates and improved model handling. Key changes ...
Read more →Ollama v0.32.15 was recently released, delivering significant performance enhancements and bug fixes for local large language model inference. A primary improvement involves caching resolved model met...
Read more →The AMD-led Lemonade SDK 11.6 was released today, August 15, 2026. This open-source software is designed for running local artificial intelligence applications with optimized large language models acr...
Read more →Ollama recently released version 0.32.9, which adds support for the NVIDIA Nemotron 3.5 Lightning model. This model is described as "an open 30B mixture-of-experts (MoE) model with 3B active parameter...
Read more →AMD GPUOpen today announced the LLM agents for automated GPU crash analysis.">RGD MCP Server, a new system designed to automate post-mortem GPU crash debugging. The server integrates large language model (LLM) agents directly into AMD's existing ...
Read more →Ollama, the framework for running large language models locally, recently released version 0.30.5. This update primarily addresses a "gemma4:12b floating point exception crash" that affected the newly...
Read more →Ollama has released version 0.23.1, introducing Gemma 4 Multi-token Processing (MTP) speculative decoding for its MLX runner. This update, primarily benefiting macOS users with Apple Silicon, can prov...
Read more →Ollama v0.23.0 was released today, introducing official support for the Claude Desktop application. This integration allows users to run both Claude Cowork and Claude Code directly within the Claude D...
Read more →Collabora announced on April 17, 2026, the integration of BitNet-style ternary Large Language Model (LLM) inference into ExecuTorch. This implementation leverages ExecuTorch's Vulkan backend to enable...
Read more →Today, the Simple DirectMedia Layer (SDL) project, a widely used cross-platform development library for games and a core component of the Steam Runtime, implemented a new policy. This policy explicitl...
Read more →An independently developed open-source Linux kernel module called GreenBoost has been reported today. It aims to augment the dedicated video memory (vRAM) on NVIDIA discrete GPUs by utilizing both sys...
Read more →Ollama released version 0.16.0 yesterday, enhancing its local large language model ecosystem with new models and a simplified command-line interface. The update introduces GLM-5, a 744 billion paramet...
Read more →Ollama released version 0.14.3 three days ago, introducing several new large language models and text-to-image capabilities. Key additions include Z-Image Turbo, a 6 billion parameter text-to-image mo...
Read more →Ollama recently released version 0.13.1-rc0, introducing several updates for local large language model development. This release addresses specific issues with CUDA VRAM discovery, which should lead ...
Read more →