Naive-N0.5-Flash
Open-weight 309B MoE model for coding and AI R&D with long context
huggingface.co/NaiveAI/Naive-N0.5-Flash
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
Naive-N0.5-Flash is NaiveAI's open-weight mixture-of-experts model aimed at coding and AI research tasks. The company describes a 309B-parameter MoE with about 15.5B active parameters per token, a native 1M-token context, and an inference stack (NaiveRT) with company-reported high decode speeds. Weights and inference code are published under the MIT license on Hugging Face, with API access also offered on naive.ai.
- Added via
- web
- Ownership
- unclaimed
Where to go
For people
- Homepagenaive.ai/en
For agents
- Homepagenaive.ai/en
- Documentationhuggingface.co/NaiveAI/Naive-N0.5-Flash
Product details
- Product kind
- Api
- Free tier
- Yes
Social profiles
Links
- Hugging Faceother