TEF 0.8B
A series of decision models on the Ollama platform designed specifically for fast binary or multiclass classification and scoring tasks. They are small, run quickly on local hardware, and are available in different parameter versions such as 0.8B, 1B, and 4B.
Timeline (last 90 days)
The TEF 0.8B version model is only 811MB in size; in actual testing, running an entire set of classification tasks with TEF 0.8B took only 0.23 seconds, while the same tasks with GPT took about 2.5 seconds.
TEF 0.8B is the smallest version, but Ollama may pull the 4B version by default, so it needs to be specified manually.
All Facts (2)
The TEF 0.8B version model is only 811MB in size; in actual testing, running an entire set of classification tasks with TEF 0.8B took only 0.23 seconds, while the same tasks with GPT took about 2.5 seconds.
50%UnverifiedTEF 0.8B is the smallest version, but Ollama may pull the 4B version by default, so it needs to be specified manually.
50%