Job 15 · Not yet tested
Easiest way to run a good model on my own machine?
Local runners. Install, load one model, answer ten prompts. We publish the hardware. Ease of install is the point of the setup score.
People who want a model on their own machine.
The standard test
Pack 0.1.0 · specified · Install, load, ten prompts
Install, load model, 10 prompts
Setup
Install the runner, load one model, and answer ten prompts. The hardware is published with the pack. Where a tool can load a shared model file, every such tool gets that file. Where it cannot, we use the tool's documented default and say so. A machine that cannot run a server is a setup result, not a reason to skip the tool.
Inputs
Install docs, the model choice, and ten prompts.
Time limit
One wall-clock cap for every tool in the job. The number is published with the pack before the first run and does not move between tools.
What we record
- Install completed
- Model loaded
- Prompts completed
- Obvious failures
- Time
- Hardware
- Version
How the FitScore is built
FitScore = weighted average × 20, rounded to the nearest integer. The weighted average is the sum of (criterion score × weight) divided by 100.
- Output quality30
- Reliability15
- Cost and free tier15
- Speed10
- Setup friction10
- Agent, API, and MCP support10
- Privacy and data10
5 excellent · 4 good · 3 usable · 2 poor · 1 fails. Full method.
Candidates
Candidates for Local / open models. This order is the launch list, not a ranking. No FitScores are published.
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Questions this page answers
- Easiest way to run a good model on my own machine?
- FitForTool has not published a FitScore for this job. The launch candidates are Ollama, LM Studio, llama.cpp, Jan, GPT4All, and vLLM. Each one is listed as not yet tested. A ranking is published only after every tool in the comparison has had the same test pack run, and a person has reviewed the result. Until that page shows a FitScore, there is no winner.
- How will FitForTool test local / open models?
- Install, load model, 10 prompts. Install the runner, load one model, and answer ten prompts. The hardware is published with the pack. Where a tool can load a shared model file, every such tool gets that file. Where it cannot, we use the tool's documented default and say so. A machine that cannot run a server is a setup result, not a reason to skip the tool. We record install completed, model loaded, prompts completed, obvious failures, time, hardware, and version. Those notes are then scored from 1 to 5 on seven shared criteria. The pack has been specified and has not been run.
- Can a vendor pay to rank higher on this job?
- No. FitForTool does not sell position or score. A sponsorship, if we run one later, is labelled and sits outside the ranked list. An affiliate link is disclosed and does not change order. A vendor may ask for a retest, and we rerun the same pack. Sponsors do not see the result before it is public.
- What does "Not yet tested" mean?
- The tool is a candidate for this job. There is no published hands-on run, so there is no FitScore, no criterion score, and no rank. Research-only is a different label, used when we have read the docs and still have not run the pack. Neither label is a score.