# Ollama v0.1.45 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.1.45
- **Released:** Jun 15, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.1.45/

## Executive Summary (TL;DR)
Ollama v0.1.45. Source highlight: DeepSeek-Coder-V2: A 16B & 236B open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

## New Features
- Introduced a workaround for AMD Vega RX 56 SDMA support on Linux

## Improvements
- DeepSeek-Coder-V2: A 16B & 236B open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
- Enhanced GPU discovery and multi-gpu support with concurrency

## Bug Fixes
- Fix memory prediction for `deepseek-v2` and `deepseek-coder-v2` models