Install this package:
emerge -a sci-ml/ollama
| Version | EAPI | Keywords | Slot |
|---|---|---|---|
| 0.31.2-r90 | 8 | ~amd64 | 0 |
| 0.31.1-r90 | 8 | ~amd64 | 0 |
<pkgmetadata> <maintainer type="person"> <email>iohann.s.titov@gmail.com</email> <name>Ivan S. Titov</name> </maintainer> <use> <flag name="cuda">Build the CUDA (cuda_v13) llama-server GPU backend via <pkg>dev-util/nvidia-cuda-toolkit</pkg></flag> <flag name="rocm">Build the ROCm/HIP (rocm_v7_2) llama-server GPU backend</flag> <flag name="vulkan">Build the Vulkan llama-server GPU backend</flag> </use> <upstream> <remote-id type="github">ollama/ollama</remote-id> </upstream> </pkgmetadata>
Manage flags for this package:
euse -i <flag> -p sci-ml/ollama |
euse -E <flag> -p sci-ml/ollama |
euse -D <flag> -p sci-ml/ollama
| Flag | Description | 0.31.2-r90 | 0.31.1-r90 |
|---|---|---|---|
| cuda | Build the CUDA (cuda_v13) llama-server GPU backend via <pkg>dev-util/nvidia-cuda-toolkit</pkg> | ✓ | ✓ |
| rocm | Build the ROCm/HIP (rocm_v7_2) llama-server GPU backend | ✓ | ✓ |
| vulkan | Build the Vulkan llama-server GPU backend | ✓ | ✓ |
| Type | File | Size | Versions |
|---|---|---|---|
| DIST | ollama-llama.cpp-b9840.tar.gz | 35092219 bytes | 0.31.1-r90 |
| DIST | ollama-llama.cpp-b9888.tar.gz | 35116234 bytes | 0.31.2-r90 |
| Type | File | Size |
|---|---|---|
| DIST | ollama-0.31.1-deps.tar.xz | 84642244 bytes |
| DIST | ollama-0.31.1.gh.tar.gz | 28933091 bytes |
| DIST | ollama-0.31.2-deps.tar.xz | 83159192 bytes |
| DIST | ollama-0.31.2.gh.tar.gz | 28856849 bytes |