devtake.dev — LlamaArticles on devtake.dev covering Llama.https://devtake.dev/en-usOne model per chip: AMD bought Taalas, whose test part hit 17,000 tokens a secondhttps://devtake.dev/article/amd-taalas-hardwired-model-silicon/https://devtake.dev/article/amd-taalas-hardwired-model-silicon/Taalas casts a model's weights into transistors. Its 6nm test chip served Llama 3.1 8B at roughly 17,000 tokens per second, and AMD just bought the company.Mon, 10 Aug 2026 08:30:00 GMThardwareamdai-chipscustom-siliconsemiconductorai-infrastructureacquisitionsnvidiahardwarehiro-tanakaArcee's Trinity-Large-Thinking is a 399B open MoE that costs 96% less than Opushttps://devtake.dev/article/arcee-trinity-large-thinking-reasoning/https://devtake.dev/article/arcee-trinity-large-thinking-reasoning/Arcee released Trinity-Large-Thinking on April 1: a 399B-param sparse MoE with 13B active, Apache 2.0 weights, $0.88 per million output tokens, and PinchBench just behind Opus 4.6.Mon, 27 Apr 2026 13:00:00 GMTopen-sourcearceetrinityllmai-modelsopen-weightsmoereasoningapache-2-0soren-vanek