Rust distroless OpenAI gpt-oss-20b cuda inference - GPU
441
GPU Version - gpt-oss-20b-Q5_K_M.gguf
21B parameters with 3.6B active parameters. Best for deep research pipeline small model steps
Endpoint: http://localhost:8080/v1/chat/completions
Repo: unsloth/gpt-oss-20b-GGUF
Content type
Image
Digest
sha256:f4349214a…
Size
10.2 GB
Last updated
9 months ago
docker pull docdbrown/gpt-oss-20b:1.0.1