Tools for running LLMs locally
Every tool on this site in one place. They run in your browser, send nothing anywhere, and use the same calculations as the rest of the site.
New tools
KV cache & context calculator
How much memory 32K, 64K or 128K tokens of context add, per model, KV type and runtime.
Agent harness × local model matrix
Which coding agent works with which local model on your hardware, with the context to set.
Hardware import
Paste one command’s output and get your GPU, VRAM and RAM filled in for the analyzer.
Calculators and checkers
Can I run this LLM?
Pick your GPU or Mac and see every model that fits, with a speed range.
Model Finder
New to local AI? Pick a goal and a computer, get one plan.
VRAM & fine-tuning calculator
Memory for one model at a chosen quant, context and batch, including LoRA and QLoRA.
Upgrade advisor
Keep, add RAM, change GPU or rent: what to do to run a model you want.
Best GPU by workload
The strongest card for coding, RAG, agents or vision at your budget.
PC build planner
A parts list sized for the models you want to run.
Local vs cloud cost
Break-even between a local GPU and hosted APIs.
Compare models
Two or more models side by side: memory, speed and quality.
Benchmarks
Measured and estimated tokens per second by GPU and model.
Decision request builder
Build a /v1/systemone request and export curl, Python or JS.
Every figure comes from one compute module; the formulas are published on the methodology page.