Related AI news
Ollama now runs Jev-like decision models locally, including Nimble
Ollama says Jev-like decision models now run entirely on a local machine. Nimble can be installed with ollama pull nimble and used through a new local /v1/systemone API.
Google DeepMind's EmbeddingGemma 2 is now available on Ollama
Ollama has added support for Google DeepMind's EmbeddingGemma 2, allowing developers to run the multimodal on-device embedding model locally.
Reflection introduces Beam open agentic model with 501B parameters
Reflection announced Beam, an open agentic AI model with 501B total parameters and 23B active parameters, scheduled to release full weights this month. Ollama also stated that more US models are coming to its platform.
Hassan trains Tev1 0.8B, a tiny Jev-like classifier
The model runs entirely on his Mac through Ollama and, by his account, classifies tasks in about 50 ms end to end. Weights and benchmarks are not available yet; Hassan says both will be released very soon.
Together AI releases tev1-4B-experimental on Together serverless
The Jev-like classifier is finetuned on Qwen3.5 4B and priced at $0.042/M input and $0/M output. Together AI is also releasing a data recipe and a finetuning tutorial, and says training Tev1 cost $17.