ollama
Get up and running with Llama 3, Mistral, Gemma, and other language models.
homepage ↗ github: ollama/ollama
Available in
| Overlay | Newest | Ebuilds | Last activity | |
|---|---|---|---|---|
| dev1990-overlay GitHub ↗ | 0.5.7-r1 | 1 | 8 mo | details › |
Versions & arches
Use flags of 0.5.7-r1
- cuda Enable NVIDIA CUDA support
- systemd Enable systemd support
- video_cards_amdgpu
6 expansion flags (python targets, ABIs, cpu flags…)
- cpu_flags_x86_avx
- cpu_flags_x86_avx2
- cpu_flags_x86_avx512f
- cpu_flags_x86_avx512vbmi
- cpu_flags_x86_avx512_vnni
- cpu_flags_x86_avx512_bf16