skills.rest
Geargrindadmin
GeargrindadminCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

llmfit-advisor

Analyze local CPU, RAM, and GPU/VRAM to recommend LLM models with quantization and fit scores.

Updated Mar 7, 2026
Search Tags:#performance#llm#hardware#recommendation#quantization#local models
One-click install
npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill llmfit-advisor-geargrindadmin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llmfit-advisor
Source: https://github.com/Geargrindadmin/gg-agentic-harness/tree/main/third-party/llmfit/skills/llmfit-advisor
Command: npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill llmfit-advisor-geargrindadmin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps users identify and select the most suitable local Large Language Models (LLMs) that can run efficiently on their specific hardware, optimizing for performance and fit.

Core Features & Use Cases

  • Hardware Detection: Automatically detects system specifications including CPU, RAM, and GPU/VRAM.
  • Model Recommendation: Recommends local LLMs with optimal quantization, speed estimates, and fit scoring based on detected hardware.
  • Use Case: A user wants to run a local LLM for coding assistance but is unsure which models their machine can handle. This Skill analyzes their hardware and suggests the best-fitting coding models, along with their recommended quantization levels and estimated performance.

Quick Start

Run llmfit to recommend the best local LLM models for your system.

Frequently Asked Questions about llmfit-advisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find the best local LLMs for my hardware specifications?▼

Finding the best local LLMs for your hardware involves analyzing your CPU, RAM, and GPU VRAM to recommend optimal models. This tool provides quantization levels, speed estimates, and fit scores to ensure efficient local model performance.

What local LLM quantization should I use for my GPU VRAM?▼

Determining the right local LLM quantization for your GPU VRAM requires analyzing your system capabilities. This tool evaluates your hardware and recommends the best quantization level to balance model speed and performance fit.

Can I filter local model recommendations by specific use cases like coding?▼

Filtering local model recommendations by specific use cases like coding is fully supported. The tool allows filtering by use case and minimum fit level, ensuring recommended LLMs match your intended application and hardware performance.

Does this tool automatically detect CPU and RAM for LLM recommendations?▼

Automatic detection of CPU and RAM specifications is used for LLM recommendations. Hardware detection includes system memory and processor analysis, alongside GPU VRAM, to accurately score model fit and estimate local execution speed.

How do I estimate local LLM speed before downloading a model?▼

Estimating local LLM speed before downloading is done by analyzing your hardware capabilities to provide performance estimates. The tool calculates speed metrics and fit scoring based on your CPU, RAM, and GPU VRAM to recommend optimal models.

Related Skills

Explore More Software Engineering Skills→
ThierryNThierryN
77

system-context

Document hardware specifications, recovery history, and database backup locations.

Community
Basic
ihatesea69ihatesea69
3

llama-cpp

Run GGUF quantized LLM inference on CPU, Apple Silicon, and consumer GPUs.

Community
Advanced
SignmanalSignmanal
1

llama-cpp

Run local GGUF model inference with llama.cpp across CPU and GPU hardware.

Community
Intermediate
Tommy-ywTommy-yw
539

llama-cpp

Run local inference and discover llama.cpp models from Hugging Face Hub.

Community
Advanced