Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Ollama v0.40.8 adds Recursive's Flint coding model with 262K context

AI summary

Ollama release v0.40.8 brings Recursive's Flint coding model into its model library, runnable with the command ollama run flint. According to the changelog, Flint is designed for repository-scale coding-agent work such as understanding unfamiliar code, tracing bugs, implementing features and adding tests, aided by reasoning, multi-turn tool use and a 262K-token context window. The model is described as an Apache 2.0-licensed 40B-parameter mixture-of-experts with roughly 2.5B parameters active per token, and Recursive's own release evaluations report 54.9% on Terminal-Bench 2.1 and 74.2% on SWE-bench Verified; Ollama notes Flint is currently supported on macOS, with other GPU support to follow in a later release.

In-depth insight

A 40B open-weight, agent-oriented coding model is now one command away for Ollama users, though its benchmark figures come from the vendor and only macOS is supported at launch.

Recursive Flint

Flint brings Recursive's coding model to Ollama. It is designed for the work coding agents do across a repository: understanding unfamiliar code, tracing bugs, implementing features, and adding tests. Reasoning, multi-turn tool use, and a 262K-token context window support longer tasks across files and tool interactions.

Flint is an Apache 2.0-licensed, 40B-parameter mixture-of-experts model with approximately 2.5B parameters active per token. In its release evaluations, Recursive reports 54.9% on Terminal-Bench 2.1 and 74.2% on SWE-bench Verified.

ollama run flint

Note: Flint is supported on MacOS. Other GPU support will be enabled in a subsequent release.

Full Changelog: v0.40.7...v0.40.8

#Recursive#Flint#Ollama

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.