Ollama released v0.40.5 on October 14, 2026. The release adds two NVIDIA vision-language models and moves decision models to the cloud. Read the release notes.
Nemotron 3.5 Super and Bolt
Nemotron 3.5 Super is a vision-language model for coding, reasoning, tool use and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture-of-experts backbone (12B active per token) with a C-RADIO vision encoder, and supports tool calling, an on/off thinking mode and context up to 1M tokens:
ollama run nemotron-3.5-superA compact sibling, Nemotron 3.5 Bolt, distills Super down to 74B parameters (9B active), tuned to fit a 24 GB NVIDIA GPU for everyday agentic tasks, with speculative decoding via its included drafter.
Other changes
- Decision models are now available on the cloud:
clef:cloudandclef-flash:cloudrun them through the ollama.com cloud without pulling them locally. - Continuing an OpenAI-compatible Responses conversation that includes custom tool calls no longer fails with an error.
- Cloud access failures now produce clearer error messages covering sign-in problems, payment issues in the desktop app and upstream errors from the ChatGPT gateway.
- llama.cpp (adding Nemotron 3.5 support) and MLX were updated.
This report covers the October 14 release notes; earlier versions are covered in our reports on v0.40.4 and v0.40.3.