cd /news/large-language-models/flint-40b-recursives-coding-model-wa… · home › topics › large-language-models › article
[ARTICLE · art-157409] src=byteiota.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Flint 40B: Recursive’s Coding Model Was Built Mostly by AI

Recursive Superintelligence released Flint, a 40B-parameter mixture-of-experts coding model that runs locally at 125 tokens per second and was built in 4 months largely through an AI research loop rather than human engineering, according to byteiota. The release points to AI-driven model development as a faster path to producing specialized coding models.

read1 min views1 publishedOct 25, 2026

Recursive Superintelligence's Flint is a 40B MoE coding model that runs at 125 tok/sec locally — built in 4 months by an AI research loop, not humans.

The post Flint 40B: Recursive’s Coding Model Was Built Mostly by AI appeared first on byteiota .

── more in #large-language-models 4 stories · sorted by recency
── more on @recursive superintelligence 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/flint-40b-recursives…] indexed:0 read:1min 2026-10-25 · —