Notes on software, systems, and side quests

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Tags power-efficiency

Tag

power-efficiency 1

RTX 3090 Power Limit: Finding the Sweet Spot for Local LLM Inference Apr 28, 2026

Recently Updated

rocket-cli: a Rocket.Chat MCP server with a local FTS5 brain
Design Fluency Meets the Knowledge Graph
How a Cryptominer Spent Two Days on My Server — and How I Found It
When your VLM test flake is actually a VNC capture race
Turbo3 + MTP: Merging Two llama.cpp Forks

Trending Tags

local-llm llama.cpp llm sqlite automation CUDA llama-cpp qwen Qwen speculative-decoding

© 2026 Jean Brito. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

local-llm llama.cpp llm sqlite automation CUDA llama-cpp qwen Qwen speculative-decoding

A new version of content is available.