Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
# Strata on an AMD card. gfx120X image: RX 9000 series and Radeon AI PRO R9700 (RDNA4). gfx110X image: RX 7000 series (RDNA3).
# Needs the amdgpu kernel driver on the host (the ROCm user-space is in the image).
#
# cp .env.example .env
# docker compose -f docker-compose.amd.yml up -d
#
# Images: ghcr.io/niko1221/strata (published from 0.2.1 on). To use one you built yourself: STRATA_IMAGE=strata:0.2.7-<flavor> docker compose up -d
services:
strata:
image: ${STRATA_IMAGE:-ghcr.io/niko1221/strata:0.2.7-rocm-gfx120x}
container_name: strata
restart: unless-stopped
ports:
- "${STRATA_BIND:-127.0.0.1}:${STRATA_PORT:-8080}:8080"
environment:
MODEL: ${MODEL:-}
MODEL_PATH: ${MODEL_PATH:-} # GGUF files you already have, as seen inside the container (mount them below)
CONTEXT: ${CONTEXT:-32k}
PARALLEL: ${PARALLEL:-}
VISION: ${VISION:-off}
TUNE: ${TUNE:-skip}
API_KEY: ${API_KEY:-}
volumes:
- strata-data:/data
# - /srv/gguf/IQ3_XXS:/models:ro
devices:
- /dev/kfd:/dev/kfd
- /dev/dri:/dev/dri
group_add:
- video
- "${RENDER_GID:-render}" # the host's render group id: getent group render | cut -d: -f3 (needed if you add `user:`; root does not need it)
ulimits:
memlock: { soft: -1, hard: -1 }
shm_size: 2gb
stop_grace_period: 2m
# security_opt: [seccomp:unconfined] # only if the log says a ROCm call was blocked (rare)
volumes:
strata-data: