Ollama (Inference Runtime)
Open weights
Params
671B MoE (4-bit Quantized)Context
128kSpeed
—Release
Jan 2025Ollama (Inference Runtime)
Leading local AI runtime and quantization distribution platform supporting one-click execution of open weights models.
Models by Ollama (Inference Runtime) (2)
Ollama (Inference Runtime)
Open weights
Params
70B (4-bit Quantized)Context
128kSpeed
—Release
Dec 2024