Ollama 0.40.6 adds Clef cloud support and q2_0 types
Updated Ollama
Summary
Ollama’s October 16 release adds Clef in its cloud service, GGUF q2_0 types and a Windows runner cleanup fix.
- Tool
- Ollama
- Category
- Agent infra
- Date
- Open source
- Yes
- License
- MIT
- Pricing
- Self-hosting and model-provider charges are separate; no hosted free allowance is promised.
Ollama published v0.40.6 on October 16, 2026. The release combines a cloud-model addition with runtime compatibility and Windows process-management changes.
What changed
- The release notes add Clef to Ollama’s cloud service. This is a hosted integration, not evidence that Clef weights are available to download or run offline.
- GGUF handling adds q2_0 tensor and file types. This does not establish that every model supports that representation or that quality and memory use have been independently measured.
- Windows runner cleanup aims to prevent orphaned runner processes.
- Question keys for the CLI’s ask mode now use identifiers.
Which users should care?
Cloud users can inspect the newly supported model in Ollama’s service; Windows users and GGUF integrators should review the corresponding compatibility changes before upgrading. The upstream release links its full comparison against v0.40.5; use the official tagged build rather than inferring installation instructions from this summary.
License and costs
The Ollama software license is MIT. It does not determine the license of model weights or the price of cloud inference. The cited release does not give a Clef price or usage allowance, so neither is promised here.
See the Ollama hub and agent infrastructure.
More from Ollama
Ollama 0.40.2 upgrades downloaded models for llama.cpp
OllamaOllama v0.40.2, released October 8, 2026, upgrades previously downloaded models in the background for llama.cpp and keeps backups for safe downgrades.
Category: Coding agents
Pricing: Open source
Questions
What is Ollama?
According to its site, Ollama gives access to the latest open models with privacy, locally or in the cloud. The repository describes it as a way to get up and running with models such as Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen and Gemma.
Is Ollama open source?
The GitHub API reports the ollama/ollama repository license as MIT.
What is the latest launch tracked here?
Ollama v0.40.2, published October 8, 2026, which upgrades previously downloaded models in the background for llama.cpp.
Filed on Agent Radar. Claims in this note are limited to the sources above.