ermantrout
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Is vibe coding worth it? What the numbers say (okaneland.com)
- Unified Memory, Explained: Why Mini PCs Can Run 70B Models a Big GPU Can't (vettedconsumer.com)
- The AI UGC ad math: $2 a video, and the bill nobody prices in (okaneland.com)
- AI agents finish a third of the job, and the math says why (okaneland.com)
- Qwen-AgentWorld-35B-A3B: a local 'world model' you can run at home Open Models (vettedconsumer.com)
- Show HN: A calculator for what an AI product keeps after costs (okaneland.com)
- The economics of a one-person AI business (okaneland.com)
- Show HN: Local LLM Hardware Calculator (vettedconsumer.com)
- GLM-5.2: The Most Powerful Open Model yet and the Brutal Reality of Running It (vettedconsumer.com)
- Prompt processing vs. generation: two phases, opposite bottlenecks (vettedconsumer.com)
- Why long context eats your VRAM: the KV cache explained (vettedconsumer.com)
- Show HN: Quant Picker – which GGUF file fits your model and machine (vettedconsumer.com)
- Mixture-of-Experts (Moe), Explained: Why "Active Parameters" Decide What Runs (vettedconsumer.com)
- GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization (vettedconsumer.com)
- GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization (vettedconsumer.com)