# Ollama v0.40.6 adds GGUF q2_0 tensor support

> **Key takeaway:** Ollama v0.40.6 introduces support for q2_0 tensor and file types in the GGUF format.

**Published:** 2026-10-17T00:58:39+00:00 
**Source:** Ollama Local AI Runtimes 
**Category:** ai-local-edge 
**Canonical URL:** https://fosswire.org/news/ollama-v0406-adds-gguf-q20-tensor-support.html 

## Summary
The Ollama v0.40.6 pre-release includes updates to the GGUF model format and Windows runner stability. It adds support for q2_0 tensors and introduces identifier-based question keys for the --ask mode.

## Technical updates in v0.40.6
- **GGUF support**: Added support for **q2_0** tensor and file types.
- **Windows**: Implemented a fix to prevent orphaned runners.
- **CLI**: Updated `--ask` mode to use identifiers for question keys.