{"slug": "llm-across-different-generation-gpus-rdna3-and-rdna4", "title": "LLM across different generation GPUs (RDNA3 and RDNA4)?", "summary": "A user on the Level1Techs forum asks whether local large language models can be run across both an AMD Radeon RX 7900 XT and a Radeon Pro R9700, noting the R9700's extra 12GB VRAM would bring combined capacity to 42GB, and questions if mixing GPU generations (RDNA3 and RDNA4) would work. The post highlights a common concern among AI enthusiasts about multi-GPU LLM inference with heterogeneous hardware.", "body_md": "[Hondo](https://forum.level1techs.com/u/Hondo)\n1\nSimple question. Probably a complex answer. I have an 7900XT which I’ve dabbled with local LLMs on but I need more VRAM and will likely get a Radeon Pro R9700. The extra 12GB will be enough (it’s never enough!) but I’d like to get a little boost by having the 42GB of both cards if it’s possible to run models and context across both.\n\nI’m new to this but I have a hunch trying to mix generations probably wouldn’t work well. Is that so?", "url": "https://wpnews.pro/news/llm-across-different-generation-gpus-rdna3-and-rdna4", "canonical_source": "https://forum.level1techs.com/t/llm-across-different-generation-gpus-rdna3-and-rdna4/254920#post_1", "published_at": "2026-09-03 12:39:45+00:00", "updated_at": "2026-09-03 12:56:04.441604+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure"], "entities": ["AMD", "Radeon RX 7900 XT", "Radeon Pro R9700", "Level1Techs"], "alternates": {"html": "https://wpnews.pro/news/llm-across-different-generation-gpus-rdna3-and-rdna4", "markdown": "https://wpnews.pro/news/llm-across-different-generation-gpus-rdna3-and-rdna4.md", "text": "https://wpnews.pro/news/llm-across-different-generation-gpus-rdna3-and-rdna4.txt", "jsonld": "https://wpnews.pro/news/llm-across-different-generation-gpus-rdna3-and-rdna4.jsonld"}}