Show HN: Tokenstead, find AI models for your hardware

Tokenstead, a new web tool, lets users select their hardware to find compatible open AI models with speed estimates and cloud-pricing comparisons, aiming to enable local AI model usage independent of vendors or governments. The platform also tracks who is running what models, citing sources like Bloomberg's report on Microsoft replacing OpenAI/Anthropic models with in-house MAI models.

Find the right model for your hardware Run AI on hardware you own, so no vendor or government order can switch off the model you depend on. Pick your rig and see which open models fit - with honest speed estimates, cloud-pricing comparisons, and a source-cited tracker of who's running what. 01 - Select your hardware click to compare AMD Ryzen AI Halo 128GB 128GB UNIFIED /find/results?hardware id=56&use case=coding Framework Desktop 128GB 128GB UNIFIED /find/results?hardware id=55&use case=coding GMKtec EVO-X2 128GB 128GB UNIFIED /find/results?hardware id=54&use case=coding Mac Mini M4 16GB 16GB UNIFIED /find/results?hardware id=23&use case=coding Mac Mini M4 Pro 24GB 24GB UNIFIED /find/results?hardware id=24&use case=coding Mac Mini M4 Pro 48GB 48GB UNIFIED /find/results?hardware id=25&use case=coding Mac Studio M4 Max 36GB 36GB UNIFIED /find/results?hardware id=26&use case=coding Mac Studio M4 Max 64GB 64GB UNIFIED /find/results?hardware id=27&use case=coding Mac Studio M4 Max 96GB 96GB UNIFIED /find/results?hardware id=28&use case=coding On a budget? Compare own vs rent → /budget?monthly budget=100&team size=1&use case=coding Count tokens & estimate API cost → /token-counter 02 - Save your rig free Sign in with GitHub to save your hardware. New here? We'll guide you through picking your rig - Mac, multi-GPU up to 8x , or custom specs - then show you exactly which models you can run locally. Sign in with GitHub - free /login Top models by quality Browse all models /models 01 DeepSeek V4 Pro MoE 1600.0B params - 1000k ctx 89 /models/deepseek-v4-pro 02 GLM 5.2 MoE 744.0B params - 1000k ctx 88 /models/glm-5-2 03 Qwen3.6 35B A3B MoE 35.0B params - 262k ctx 87 /models/qwen3-6-35b-a3b 04 DeepSeek V3 0324 MoE 671.0B params - 128k ctx 87 /models/deepseek-v3-0324 05 DeepSeek V4 Flash MoE 284.0B params - 1000k ctx 86 /models/deepseek-v4-flash 06 LongCat 2.0 MoE 1600.0B params - 1000k ctx 86 /models/longcat-2-0 Who's running what See all 22 → /adoption Bloomberg: Microsoft replacing OpenAI/Anthropic models with in-house MAI models in Excel and Outlook to cut inference spend; a tuned MAI variant claims GPT-5.4 parity at up to 10x efficiency. Proprietary not open-weight , but the same frontier-API cost pressure. Self-hosted Llama 3.1 8B on Kubernetes automates support-ticket creation and resolution drafts for the ad-tech platform; 80% less time to create tickets. Mistral Medium 3.5 128B for up to 100k French public-sector agents under a 4-year, EUR 140M framework; on-prem SecNumCloud option for sovereignty. Self-hosted Codestral in its RAISE/SovBox coding assistant for regulated aerospace, defense and public-sector clients; code-completion accuracy 50% - 90%. Self-hosted, 100% European Codestral powers multilingual SBB rail support bots 1k - 30k employees, 80% fewer repetitive queries and an accounting accruals agent. Statuses: confirmed official source reported credible third-party, not officially confirmed testing evaluating, not deployed. Curated and source-cited, not a scraper. Built a rig worth sharing? Browse shared builds → /rigs .