Impact Score: 5/10
Ollama v0.1.6 — 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.
⚡ Executive Summary (TL;DR)
Ollama v0.1.6. Source highlight: Dolphin 2.1 Mistral: an instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.
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.
⚡ Performance & Enhancements (2)
- Zephyr Beta: this is the second model in the series based on Mistral, and has strong performance that compares to and even exceeds Llama 2 70b in several categories. It’s trained on a distilled dataset, improving grammar and yielding even better chat results.
- Slight performance improvements for all models
🔧 Bug Fixes & Patches (5)
- Fixed various issues when writing prompts in `ollama run`
- Fixed trailing slashes causing an error when using `OLLAMA_HOST`
- Fixed issue where `ollama pull` would retry multiple times when out of space
- Fixed various `out of memory` issues when using Nvidia GPUs
- Fixed performance issue previously introduced on AMD CPUs
📄 View Raw Release Notes (Original Developer Log)
## New models
* [Dolphin 2.1 Mistral](https://ollama.ai/library/dolphin2.1-mistral): an instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.
* [Zephyr Beta](https://ollama.ai/library/zephyr): this is the second model in the series based on Mistral, and has strong performance that compares to and even exceeds Llama 2 70b in several categories. It’s trained on a distilled dataset, improving grammar and yielding even better chat results.
## What's Changed
* Pasting multi-line strings in `ollama run` is now possible
* Fixed various issues when writing prompts in `ollama run`
* The library models have been refreshed and revamped including `llama2`, `codellama`, and more:
* All `chat` or `instruct` models now support setting the `system` parameter, or `SYSTEM` command in the `Modelfile`
* Parameters (`num_ctx`, etc) have been updated for library models
* Slight performance improvements for all models
* Model storage can now be configured with `OLLAMA_MODELS`. See the [FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-can-i-change-where-ollama-stores-models) for more info on how to configure this.
* `OLLAMA_HOST` will now default to port `443` when `https://` is specified, and port `80` when `http://` is specified
* Fixed trailing slashes causing an error when using `OLLAMA_HOST`
* Fixed issue where `ollama pull` would retry multiple times when out of space
* Fixed various `out of memory` issues when using Nvidia GPUs
* Fixed performance issue previously introduced on AMD CPUs
## New Contributors
* @ajayk made their first contribution in https://github.com/jmorganca/ollama/pull/855
**Full Changelog**: https://github.com/jmorganca/ollama/compare/v0.1.5...v0.1.6