Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agents
Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
The model record exists, but no source-linked provider offer is available yet.
Submit a sourceRecorded from the source catalog and provider listings.
recursive/flintWeights: Hugging Face ↗ · Hugging Face (INT4) ↗
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.
Read the methodologyField-level changes detected between successful source imports.
This record has not changed within the retained import history.
Every figure on this page traces back to one of these records.
Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
GET https://modelbench.lol/api/v1/models/recursive/flintcurl "https://modelbench.lol/api/v1/models/recursive/flint"Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agents. It is published by Recursive and catalogued here from Models.dev.
Flint accepts up to 262K tokens of context and returns up to 262K output tokens.
Yes. The weights are published and downloadable from Hugging Face, Hugging Face (INT4) under the Apache-2.0 license.
The catalog records a release date of 2026-10-21, last verified Oct 24, 2026.