Laser and other tech projects,
always free for your use.
Every post has the details, process, and exact settings to duplicate it yourself. The site is live and maintained — and most of the work here, including this site itself, is done with LLMs.
MakoBench
Language models scored on code and chat with one open test suite, run on our own hardware. Suite 4.0.
- deepseek-flash 19.2
- deepseek-pro 17.5
- swish-31b-final-q8-0-hb16 16.1
Latest projects
Builds, guides, and experiments from the shop.
What MakoBench Tests, and What It Doesn't
MakoBench tests text models on two jobs, working code and role-play or companion chat. Here is which models belong on the board, which never will, and what a row needs before it gets a rank.
MakoBench Suite History: Earlier Versions
The MakoBench tests change from time to time, and a score only means something inside the suite that produced it. Here is where the earlier boards live and why we kept them.
MakoBench Suite 4.0: Nominal 20, Class and Lean
Suite 4.0 scores Code and Chat at 10 each instead of a percentage, drops the slowest and noisiest tests, and adds Class and Lean. Here is what the public release changed and what is in our own copy of the tool but not yet in a release.
Run CrucibleForge on Your Own Models: Install Guide
Install CrucibleForge, the open-source engine behind MakoBench, point it at any OpenAI-compatible model and get Code and Chat scores, 10 each for a perfect standard run. Real commands, real output, and a 1.6-minute smoke test that cost 2 cents.
How MakoBench Works: Open LLM Benchmark Explained
MakoBench is our public LLM benchmark board: 29 models, one Total (Code plus Chat), an error margin on every score. The engine underneath is CrucibleForge, free and open source. Here is what it tests, how it judges, and what the board cannot tell you.
MIT-0 license: why every Laser Lloyd project uses it
Every open-source project we publish now carries MIT-0, the MIT licence with the attribution requirement removed: take the code, change it, put it in a product you sell, and you do not have to keep our notice or credit us.
Nov updates 2026: DisPatch 4.3, StudioForge 2.3 and more
What shipped on 1 November 2026: DisPatch Chat 4.3.0, StudioForge 2.3.0, MailForge 0.7.1 and five more, with upgrade notes.
My AI Agent Built a Benchmarking Tool for My AI Agents
Our coding agent wrote bench-llm: 1,660 lines of Python that benchmark local models in LM Studio. Within two weeks our models all scored 5/5, so we replaced it with CrucibleForge: 276 cases, 166 hard, free on GitHub.
What My AI Agents Actually Cost: DeepSeek vs the Big APIs
Five months of an always-on AI agent stack: $242, $225, $385, then $293 in September and October once a $55 MiniMax plan took most of the traffic. What drove each bill, what DeepSeek's price hike did, and what happened when the flat plan ran out.
Browse by type
AI & Local LLM
Running AI on your own hardware — local LLMs, agents, and image generation. No subscriptions, no cloud, no computer-science degree.
Laser Projects
Cutting, engraving, and the occasional small fire. Each post has the details, process, and settings you need to duplicate it yourself.
Tools & Downloads
Small apps and utilities we built and actually use. Free downloads for personal use, source included.