github rjmalagon/ollama-linux-amd-apu v0.12.3

latest releases: v0.13.5, v0.13.3, v.0.13.1-rc0...
3 months ago

What's Changed (this repo branch)

  • Sync to v0.12.3

What's Changed (from Ollama)

New Models

DeepSeek-V3.1-Terminus: DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode. It delivers more stable & reliable outputs across benchmarks compared to the previous version:

Run (requires 500GB+ of VRAM)

ollama run deepseek-v3.1

What's Changed

  • Fixed issue where tool calls provided as stringified JSON would not be parsed correctly
  • ollama push will now provide a URL to follow to sign in
  • Fixed issues where qwen3-coder would output unicode characters incorrectly
  • Fix issue where loading a model with /load would crash

Full Changelog: v0.12.2...v0.12.3

Don't miss a new ollama-linux-amd-apu release

NewReleases is sending notifications on new releases.