sozercan/orka-aikit:qwen35-4b-recurrent-20261010

Index digest

sha256:b360b34d13e912c025296ae1ff852fd663d1d6bb87065584d7fc723f01f81c37

OS/ARCH

linux/amd64

Compressed size

4.43 GB

Last pushed

about 1 month by sozercan

Type

Image

Manifest digest

sha256:c6fa99fdd740c930c18e407c553dd28d06bf32bb2d3db59b71bc6137f17d5516

Image Layers

1pulled from ghcr.io/kaito-project/aikit/base@sha256:48c78ee9c94b3d928ac56b56da498497676f81955bdf074c258de09d8fe3f3e46.46 MB

2Copying Qwen3.5-4B-Q4_K_M.gguf to /models/Qwen3.5-4B-Q4_K_M.gguf2.52 GB

3Creating config for platform linux/amd64362 B

4Installing standard runtime CA roots124.54 KB

5Copying local-ai from OCI artifact53.72 MB

6Creating metadata.json for backend cuda12-llama-cpp1.78 GB

7Creating metadata.json for backend cpu-llama-cpp46.92 MB

8COPY /LocalAI/backend/cpp/llama-cpp/package/ /backends/cpu-llama-cpp/ # buildkit25.16 MB

Command

pulled from ghcr.io/kaito-project/aikit/base@sha256:48c78ee9c94b3d928ac56b56da498497676f81955bdf074c258de09d8fe3f3e4