Recursive Flint
Intro
**Recursive Flint** is a recently tracked product, model, or tool in public channels. The radar excerpt reads: > Recursive launched Flint: open-weight (Apache-2.0) MoE coding model, 39.8B total / ~2.5B active, 262K ctx; 74.2% SWE-bench Verified, 54.9% Terminal-Bench 2.1; >125 tok/s on M4 Pro MacBook; built via its 'Eureka Machine' recursive self-improvement. HF RecursiveSI/flint (+int4, nvfp4-gguf) created Oct 21; vLLM day-0 blog (vllm.ai/blog/2026-10-21-flint); Wall St Engine post 5k views. The recorded source label is `sitemap`. Use the public URL below to verify the original post or page.
Explain
Based only on the excerpt, **Recursive Flint** should be understood from the facts stated there. This write-up does not invent funding amounts, model sizes, or leaderboard scores that are absent from the excerpt or URL metadata. Confirmable points from the excerpt: - Recursive launched Flint: open-weight (Apache-2.0) MoE coding model, 39.8B total / ~2.5B active, 262K ctx; 74.2% SWE-bench Verified, 54.9% Terminal-Bench 2.1; >125 tok/s on M4 Pro MacBook; built via its 'Eureka Machine' recursive self-improvement. - HF RecursiveSI/flint (+int4, nvfp4-gguf) created Oct 21; vLLM day-0 blog (vllm.ai/blog/2026-10-21-flint); Wall St Engine post 5k views. The radar `score` for this entry is `0.88` (an internal ranking field, not a third-party benchmark score).
Usage
To learn more or try **Recursive Flint**, start from public sources: 1. Open the source link: <https://www.recursive.com/updates/introducing-recursive-flint> and check the official description and availability. 2. Follow any access path mentioned in the excerpt (API, open weights, waitlist, in-product entry) using official instructions. 3. Before production use, verify license terms, regional availability, and safety limits yourself; do not assume quotas, prices, or eval scores that the excerpt does not state.