Best Used GPUs for Local AI in 2026 (September 2026)
The RTX 30 and 40 series cards that still clear current Ollama and llama.cpp floors, what VRAM tier each opens, and which variants are worth the used premium.
Tag
#gpu
How much VRAM does a local LLM actually need? (August 2026)
The published GGUF file size is the weights. VRAM use also includes the KV cache, framework overhead, and your context length. The math, walked through.
What to Check Before Buying a Used GPU for Local AI
The compute capability, driver and ROCm facts to verify on a second-hand card before it has to run Ollama, llama.cpp or a current CUDA toolkit.
Local vs API Cost: Work Out Your Own Crossover Point
There is no single crossover figure. The cost components on each side, the arithmetic shape, and why every price in it carries a date.
Running Local LLMs on AMD and Intel GPUs in 2026
AMD's ROCm support splits by card and by OS, Intel archived both of its own LLM libraries this year, and llama.cpp is the path still standing.
EU Opens Formal Antitrust Investigation Into NVIDIA's GPU Dominance
Brussels is probing whether NVIDIA bundles GPUs with networking equipment and uses CUDA lock-in to crush competitors. The investigation could take years.
DeepSeek's Engram: The Memory Trick That Bypasses GPU Restrictions
China's most innovative AI lab published a technique that lets large language models store knowledge in cheap system RAM instead of expensive GPU memory. It's a direct response to US export controls -- and it works.