Home / AI / Ollama / v0.12.4
Ollama v0.12.4stable Released Oct 03, 2025
Impact Score: 5/10

Ollama v0.12.4 — Release Notes & Engineering Impact

Source available — automated, not human-reviewed

Component: ollama · Channel: stable. Automated analysis, not a compatibility certification. How this works.

Analysis updated: 2026-11-01.

Compatibility not verified — check source notes
📄 .MD
🔧 Bug Fixes 5
⚡ Executive Summary (TL;DR)

Ollama v0.12.4. Source highlight: Flash attention is now enabled by default for Qwen 3 and Qwen 3 Coder

Visit Ollama Official Site ↗ Official Release Source ↗ All Ollama Releases 📡 Ollama RSS
Who Does This Impact? (Role-Based Analysis)

💻 Software Engineers & Devs

Check the source notes against the package and APIs you use before upgrading.

📊 Product & Engineering Leads

Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.

⚙️ DevOps & Security

Verify the target version, runtime requirements and rollback procedure in the official documentation.

🔧 Bug Fixes & Patches (5)

  • Fixed minor memory estimation issues when scheduling models on NVIDIA GPUs
  • Fixed an issue where `keep_alive` in the API would accept different values for the `/api/chat` and `/api/generate` endpoints
  • Fixed tool calling rendering with `qwen3-coder`
  • Fixed crash where templates were not correctly defined
  • Fix memory calculations on NVIDIA iGPUs
📄 View Raw Release Notes (Original Developer Log)
## What's Changed * Flash attention is now enabled by default for Qwen 3 and Qwen 3 Coder * Fixed minor memory estimation issues when scheduling models on NVIDIA GPUs * Fixed an issue where `keep_alive` in the API would accept different values for the `/api/chat` and `/api/generate` endpoints * Fixed tool calling rendering with `qwen3-coder` * More reliable and accurate VRAM detection * `OLLAMA_FLASH_ATTENTION` can now be overridden to `0` for models that have flash attention enabled by default * macOS 12 Monterey and macOS 13 Ventura are no longer supported * Fixed crash where templates were not correctly defined * Fix memory calculations on NVIDIA iGPUs * AMD gfx900 and gfx906 (MI50, MI60, etc) GPUs are no longer supported via ROCm. We're working to support these GPUs via Vulkan in a future release. ## New Contributors * @Fachep made their first contribution in https://github.com/ollama/ollama/pull/12412 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.12.3...v0.12.4-rc3
← Older Version Ollama v0.12.3