NaiveAI releases a 309-billion-parameter model with open weights
NaiveAI released Naive-N0.5-Flash with model weights and inference code under the MIT license. Its model card lists 309 billion total parameters, with 15.5 billion active for each token.
Verified 10:28 AM PDT · 1 original sources
The company says the model supports a million-token context using local and sparse attention. It builds on Xiaomi's MiMo-V2.5 base model.
Open weights do not make this a small desktop model. The company says the compressed weights alone take roughly 315 gigabytes, before the extra memory needed to run the model. The company remains the only source for the performance figures.
Independent coding tests need to measure performance and memory use with long contexts. Buyers also need to know the cost of each completed task, including retries and review.
Audit the story
Original sources
Company claims remain company claims. Follow the reporting and judge the evidence directly.
Continue the edition