What Is an AI PC NPU? What It Does, What TOPS Mean, and Whether It Helps Local LLMs
What is an AI PC NPU? What TOPS mean, what Copilot+ PCs require, how NPUs differ from GPUs for local LLMs, and whether an NPU is worth paying extra for.
-
-
LLM Context Length VRAM: How the KV Cache Works, Formulas, Worked Examples and Fixes
LLM context length VRAM guide: the KV cache formula, worked examples for 7B to 70B models, f16 vs q8_0 vs q4_0 cache, Ollama defaults and out-of-memory fixes.
-
12GB vs 16GB VRAM for Local LLMs: What Runs, and RTX 3060, 4060 Ti or 5060 Ti
12GB vs 16GB VRAM for local LLMs: which models fit, and how the RTX 3060 12GB, 4060 Ti 16GB and 5060 Ti 16GB compare on price and memory bandwidth.
-
AI PC NPU 是什么？它能做什么、TOPS 代表什么，对本地大模型有用吗（2026）
AI PC NPU 是什么：TOPS 代表什么、Copilot+ PC 的要求、NPU 与 GPU 在本地大模型上的区别、软件支持现状，以及值不值得为 NPU 多花钱。
-
KV cache 显存占用：上下文长度怎么吃显存，公式、算例与排查（2026）
KV cache 显存占用怎么算：公式、7B 到 70B 模型的算例、f16 与 q8_0、q4_0 缓存的区别、Ollama 的默认上下文，以及显存不足时的处理办法。
-
12GB 16GB 显存跑大模型：能跑什么、选 3060、4060 Ti 还是 5060 Ti
12GB 16GB 显存跑大模型怎么选？按模型体积和显存带宽对比 RTX 3060 12GB、4060 Ti 16GB、5060 Ti 16GB，附参考价与理论速度上限。
-
Best GPU for Local LLMs: A VRAM Tier Table (2026)
Find the best GPU for local LLM use: VRAM tiers from 8GB to 32GB, matching models, bandwidth, power draw and dated price ranges, plus buying pitfalls.
-
How Much VRAM Does an LLM Need? Parameters, Quantization and Context
How much VRAM does an LLM need? Use weights + KV cache + overhead to estimate from parameters, quantization and context, with quick tables for 8GB to 48GB.
-
How to Run LLMs on a Mac: How Much Unified Memory Do You Need?
How to run LLMs on a Mac: what 16GB to 128GB of unified memory can hold, usable GPU share, bandwidth by chip, and Mac vs GPU advice.
-
Mac 跑大模型：统一内存怎么选、能跑多大的模型
Mac 跑大模型要多少统一内存？按 16GB 到 128GB 对照可运行的模型、可用显存比例和带宽，并对比 Mac 与独显、给出购买建议。
