llm-cpu-gemma-chat (latest-x86_64)

Published 2026-06-18 01:44:10 +00:00 by j

Pull the image from the command line:

docker pull forge.jde.nz/public/llm-cpu-gemma-chat:latest-x86_64

Digest

sha256:39eb33fdac558a071cebe81a1ea0a50e8fe257e482987a0f29ed1a4dedd9e96b

For more information on the Container registry, see the documentation.

LLM inference in C/C++

ARG RELEASE

ARG LAUNCHPAD_BUILD_ARCH

LABEL org.opencontainers.image.version=24.04

ADD file:46ac5b8ee4c64ad9ebe840abd5619f571a617ac19483764d47d0eeba7907934f in /

CMD ["/bin/bash"]

ARG BUILD_DATE=2026-06-17T09:10:46Z

ARG APP_VERSION=b9680

ARG APP_REVISION=d5376cf5d711b9be87232b25fea82fe62d607400

ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp

ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp

LABEL org.opencontainers.image.created=2026-06-17T09:10:46Z org.opencontainers.image.version=b9680 org.opencontainers.image.revision=d5376cf5d711b9be87232b25fea82fe62d607400 org.opencontainers.image.title=llama.cpp org.opencontainers.image.description=LLM inference in C/C++ org.opencontainers.image.url=https://github.com/ggml-org/llama.cpp org.opencontainers.image.source=https://github.com/ggml-org/llama.cpp

RUN |5 BUILD_DATE=2026-06-17T09:10:46Z APP_VERSION=b9680 APP_REVISION=d5376cf5d711b9be87232b25fea82fe62d607400 IMAGE_URL=https://github.com/ggml-org/llama.cpp IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp /bin/sh -c apt-get update && apt-get install -y libgomp1 curl ffmpeg && apt autoremove -y && apt clean -y && rm -rf /tmp/* /var/tmp/* && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && find /var/cache -type f -delete # buildkit

COPY /app/lib/ /app # buildkit

ENV LLAMA_ARG_HOST=0.0.0.0

COPY /app/full/llama-server /app # buildkit

WORKDIR /app

HEALTHCHECK {Test:[CMD curl -f http://localhost:8080/health] Interval:0s Timeout:0s StartPeriod:0s StartInterval:0s Retries:0}

ENTRYPOINT ["/app/llama-server"]

ARG MODEL_URL=https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF/resolve/main/gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf

RUN |1 MODEL_URL=https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF/resolve/main/gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf /bin/sh -c mkdir -p /models && curl -fL --retry 8 --retry-delay 15 --retry-connrefused -C - -o /models/model.gguf "$MODEL_URL" && test -s /models/model.gguf # buildkit

COPY llm-cpu-gemma-chat/webui/ /webui/ # buildkit

EXPOSE [8080/tcp]

ENV LLAMA_ARG_MODEL=/models/model.gguf LLAMA_ARG_STATIC_PATH=/webui LLAMA_ARG_PORT=8080 LLAMA_ARG_JINJA=1 LLAMA_ARG_THREADS=8 LLAMA_ARG_CTX_SIZE=4096

Key	Value
org.opencontainers.image.created	2026-06-17T09:10:46Z
org.opencontainers.image.description	LLM inference in C/C++
org.opencontainers.image.revision	d5376cf5d711b9be87232b25fea82fe62d607400
org.opencontainers.image.source	https://github.com/ggml-org/llama.cpp
org.opencontainers.image.title	llama.cpp
org.opencontainers.image.url	https://github.com/ggml-org/llama.cpp
org.opencontainers.image.version	b9680