---
type: "post"
id: "recursive-releases-flint-40b-model-for-local-coding-6ca7fb"
slug: "recursive-releases-flint-40b-model-for-local-coding-6ca7fb"
title: "Recursive releases Flint, 40B model for local coding Recursive unveiled Flint, a 40B MoE local coding model with 2.5B active parameters per token."
description: "Recursive has released Flint, a local mixture-of-experts coding model with 40 billion total parameters and about 2.5 billion active parameters per token."
retrieval_nugget: "Recursive has released Flint, a local mixture-of-experts coding model with 40 billion total parameters and about 2.5 billion active parameters per token."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["Recursive","Flint","rec","Eureka Machine","llama.cpp","Ollama","vLLM","SGLang"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "Recursive’s Flint release adds the model’s 40B total/2.5B active parameter configuration and its local coding capabilities to the prior Flint benchmark discussion."
prior_refs: ["memory:c2694b57-56bb-8673-aa74-8d410221fb92"]
source_url: "https://www.testingcatalog.com/recursive-releases-flint-40b-model-for-local-coding"
source_urls: ["https://www.testingcatalog.com/recursive-releases-flint-40b-model-for-local-coding"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:recursive-releases-flint-40b-model-for-local-coding-6ca7fb"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/recursive-releases-flint-40b-model-for-local-coding-6ca7fb/","markdown":"https://newruntime.com/posts/recursive-releases-flint-40b-model-for-local-coding-6ca7fb.md","json":"https://newruntime.com/posts/recursive-releases-flint-40b-model-for-local-coding-6ca7fb.json"}
---

# Recursive releases Flint, 40B model for local coding Recursive unveiled Flint, a 40B MoE local coding model with 2.5B active parameters per token.

## Retrieval answer

Recursive has released Flint, a local mixture-of-experts coding model with 40 billion total parameters and about 2.5 billion active parameters per token.

Recursive has released Flint, a local mixture-of-experts coding model with 40 billion total parameters and about 2.5 billion active parameters per token. Its weights are available under Apache 2.0.

The company says Flint supports up to 512k tokens of context, while recommending use within 256k. It lists compatibility with llama.cpp, Ollama, Unsloth, LM Studio, vLLM, and SGLang, and has also released rec, an inference engine tuned for Flint on M4 Pro, M5 Pro, and M5 Max Macs.

Recursive reports more than 125 tokens per second on an M4 Pro MacBook Pro and 150 tokens per second on a 64GB NVIDIA RTX Spark at short contexts. It says Flint leads sub-50B MoE models on SWE-Bench Pro v2, Terminal-Bench 2.1, and SWE-Bench Verified. The source does not establish independent benchmark replication, comparative performance under matching settings, or performance on longer contexts.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)