Fully Offline Local AI assistant is hungry for GPU memoryRunning Qwen3.6 27B Q8_0 with 256k context in reasoning mode loads around 50GB of the GPU memory and gives around 64 tokens/s for prompt+generation and that is quite good for a local model with that much context.Originally published on My Tech Blog:https://minox.cosmichive.com/experiences-from-setting-up-fully-offline-local-only-ai-assisted-workstation/#ai #aiagents #linux #llm
Related
Sony Xperia 10 VIII reveals new details in FCC filingSony's Xperia 10 VIII feels closer than ever after stop by FCC.http...
Sony Xperia 10 VIII reveals new details in FCC filingSony's Xperia 10 VIII feels closer than ever after stop by FCC.https://www.androidauthority.com/sony-xperia-10-viii-fcc-filing-...
📰 Troubling new details emerge on diabetes ouster controversyAmerican Diabetes Association blocked publication of op-ed ...
📰 Troubling new details emerge on diabetes ouster controversyAmerican Diabetes Association blocked publication of op-ed articles so the authors posted them as a preprint.📰 Source: ...
📰 A bug in AWS has caused some customers' bills to spike from a few cents to billions of dollars"The displayed billing e...
📰 A bug in AWS has caused some customers' bills to spike from a few cents to billions of dollars"The displayed billing estimates do not reflect actual usage and charges," Amazon sa...