Flint: a coding-agent model from Recursive you can run at home

Recursive describes Flint in its own words as "Recursive's mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token." It is built to dig through a codebase, fix bugs, add features, and write tests, and it can hold a long back-and-forth while calling outside tools, which is what an agent needs to actually do work rather than just talk. In Recursive's own evaluations, it scores 74.2% on SWE-bench Verified and 89.7% on SWE-bench Pro v2, both benchmarks built from real bugs in open-source projects. Unsloth, a team known for shrinking large models down to run on ordinary hardware, packaged it into ready local files; of the compressed options, the one unsloth labels Q4_K_XL runs about 25 GB, and a much smaller but noticeably weaker one runs about 11 GB. Because only a fraction of its parameters activate per token, it does not need to load the full 40 billion into memory at once, which is why it fits on a single well-equipped machine at all.

Set up Recursive's Flint model, packaged by unsloth for local use, for me: https://huggingface.co/unsloth/flint-GGUF — pick the file that fits my memory, run it through a GGUF-compatible local model runner, and show me how to ask it to find and fix a bug in a simple project.

💻 Minimum is a Mac or PC with 16 GB of memory (the lighter build, about 11 GB, is noticeably weaker). Comfortable is 32 GB or more — the main compressed build weighs about 25 GB.